Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2693 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.4183. Min Range: -11.4183
Max Act: 11.4183. Min Act: -0.1700
Data Index: 8005183 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.4183. Min Range: -11.4183
Max Act: 11.2308. Min Act: -0.1700
Data Index: 323581 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.4183. Min Range: -11.4183
Max Act: 11.2308. Min Act: -0.1700
Data Index: 7543650 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.4183. Min Range: -11.4183
Max Act: 11.0433. Min Act: -0.1700
Data Index: 4011590 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.4183. Min Range: -11.4183
Max Act: 11.0433. Min Act: -0.1700
Data Index: 6454615 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.4183. Min Range: -11.4183
Max Act: 10.9808. Min Act: -0.1700
Data Index: 6361221 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.4183. Min Range: -11.4183
Max Act: 10.9183. Min Act: -0.1700
Data Index: 7516170 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.4183. Min Range: -11.4183
Max Act: 10.7933. Min Act: -0.1700
Data Index: 6634615 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.4183. Min Range: -11.4183
Max Act: 10.7933. Min Act: -0.1700
Data Index: 6898155 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.4183. Min Range: -11.4183
Max Act: 10.7933. Min Act: -0.1700
Data Index: 2868092 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.4183. Min Range: -11.4183
Max Act: 10.6683. Min Act: -0.1700
Data Index: 5252785 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.4183. Min Range: -11.4183
Max Act: 10.6683. Min Act: -0.1700
Data Index: 6730226 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.4183. Min Range: -11.4183
Max Act: 10.6683. Min Act: -0.1700
Data Index: 3628653 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.4183. Min Range: -11.4183
Max Act: 10.6683. Min Act: -0.1700
Data Index: 8103773 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.4183. Min Range: -11.4183
Max Act: 10.5433. Min Act: -0.1700
Data Index: 3363533 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.4183. Min Range: -11.4183
Max Act: 10.6683. Min Act: -0.1700
Data Index: 6981432 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.4183. Min Range: -11.4183
Max Act: 10.4808. Min Act: -0.1700
Data Index: 1315741 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.4183. Min Range: -11.4183
Max Act: 10.5433. Min Act: -0.1700
Data Index: 8032253 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.4183. Min Range: -11.4183
Max Act: 10.5433. Min Act: -0.1700
Data Index: 1986752 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.4183. Min Range: -11.4183
Max Act: 10.5433. Min Act: -0.1700
Data Index: 8082012 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #19