Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 503 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6353. Min Range: -4.6353
Max Act: 4.6353. Min Act: -0.1700
Data Index: 8387633 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6353. Min Range: -4.6353
Max Act: 4.4478. Min Act: -0.1700
Data Index: 2528214 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6353. Min Range: -4.6353
Max Act: 4.3853. Min Act: -0.1700
Data Index: 3123563 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6353. Min Range: -4.6353
Max Act: 4.3228. Min Act: -0.1700
Data Index: 5999055 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6353. Min Range: -4.6353
Max Act: 4.2603. Min Act: -0.1700
Data Index: 1864520 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6353. Min Range: -4.6353
Max Act: 4.2915. Min Act: -0.1700
Data Index: 5649223 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6353. Min Range: -4.6353
Max Act: 4.1978. Min Act: -0.1700
Data Index: 2934404 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6353. Min Range: -4.6353
Max Act: 4.1978. Min Act: -0.1700
Data Index: 5527685 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6353. Min Range: -4.6353
Max Act: 4.1978. Min Act: -0.1700
Data Index: 3160568 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6353. Min Range: -4.6353
Max Act: 4.1665. Min Act: -0.1700
Data Index: 8138367 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6353. Min Range: -4.6353
Max Act: 4.1665. Min Act: -0.1700
Data Index: 5449936 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6353. Min Range: -4.6353
Max Act: 4.1665. Min Act: -0.1700
Data Index: 5727218 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6353. Min Range: -4.6353
Max Act: 4.1353. Min Act: -0.1700
Data Index: 1785728 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6353. Min Range: -4.6353
Max Act: 4.1040. Min Act: -0.1700
Data Index: 3387792 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6353. Min Range: -4.6353
Max Act: 4.1353. Min Act: -0.1700
Data Index: 626700 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6353. Min Range: -4.6353
Max Act: 4.1040. Min Act: -0.1700
Data Index: 5902824 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6353. Min Range: -4.6353
Max Act: 4.1040. Min Act: -0.1700
Data Index: 5298042 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6353. Min Range: -4.6353
Max Act: 4.0728. Min Act: -0.1700
Data Index: 3717042 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6353. Min Range: -4.6353
Max Act: 4.0728. Min Act: -0.1700
Data Index: 2151597 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6353. Min Range: -4.6353
Max Act: 4.0728. Min Act: -0.1700
Data Index: 4114806 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #19