Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4454 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1183. Min Range: -5.1183
Max Act: 5.1183. Min Act: -0.1700
Data Index: 2635585 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1183. Min Range: -5.1183
Max Act: 4.9933. Min Act: -0.1700
Data Index: 2185706 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1183. Min Range: -5.1183
Max Act: 4.8995. Min Act: -0.1700
Data Index: 257670 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1183. Min Range: -5.1183
Max Act: 4.8370. Min Act: -0.1700
Data Index: 3590373 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1183. Min Range: -5.1183
Max Act: 4.8370. Min Act: -0.1700
Data Index: 4261615 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1183. Min Range: -5.1183
Max Act: 4.7745. Min Act: -0.1700
Data Index: 2837682 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1183. Min Range: -5.1183
Max Act: 4.7745. Min Act: -0.1700
Data Index: 514162 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1183. Min Range: -5.1183
Max Act: 4.7745. Min Act: -0.1700
Data Index: 4556922 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1183. Min Range: -5.1183
Max Act: 4.7433. Min Act: -0.1700
Data Index: 4390206 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1183. Min Range: -5.1183
Max Act: 4.7120. Min Act: -0.1700
Data Index: 1975235 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1183. Min Range: -5.1183
Max Act: 4.7433. Min Act: -0.1700
Data Index: 6165397 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1183. Min Range: -5.1183
Max Act: 4.7120. Min Act: -0.1700
Data Index: 3440061 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1183. Min Range: -5.1183
Max Act: 4.7120. Min Act: -0.1700
Data Index: 510409 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1183. Min Range: -5.1183
Max Act: 4.6808. Min Act: -0.1700
Data Index: 1620071 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1183. Min Range: -5.1183
Max Act: 4.7120. Min Act: -0.1700
Data Index: 2198654 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1183. Min Range: -5.1183
Max Act: 4.7120. Min Act: -0.1700
Data Index: 1023833 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1183. Min Range: -5.1183
Max Act: 4.7120. Min Act: -0.1700
Data Index: 7182386 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1183. Min Range: -5.1183
Max Act: 4.7120. Min Act: -0.1700
Data Index: 3124122 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1183. Min Range: -5.1183
Max Act: 4.7120. Min Act: -0.1700
Data Index: 6082748 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1183. Min Range: -5.1183
Max Act: 4.6808. Min Act: -0.1700
Data Index: 3387923 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #19