Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3970 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9549. Min Range: -2.9549
Max Act: 2.9391. Min Act: -0.1700
Data Index: 5729881 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9549. Min Range: -2.9549
Max Act: 2.9549. Min Act: -0.1700
Data Index: 115487 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9549. Min Range: -2.9549
Max Act: 2.9391. Min Act: -0.1700
Data Index: 8108479 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9549. Min Range: -2.9549
Max Act: 2.9232. Min Act: -0.1700
Data Index: 8706921 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9549. Min Range: -2.9549
Max Act: 2.8439. Min Act: -0.1700
Data Index: 545838 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9549. Min Range: -2.9549
Max Act: 2.8121. Min Act: -0.1700
Data Index: 4799202 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9549. Min Range: -2.9549
Max Act: 2.8280. Min Act: -0.1700
Data Index: 2933383 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9549. Min Range: -2.9549
Max Act: 2.7962. Min Act: -0.1700
Data Index: 4856342 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9549. Min Range: -2.9549
Max Act: 2.7962. Min Act: -0.1700
Data Index: 8108476 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9549. Min Range: -2.9549
Max Act: 2.7802. Min Act: -0.1700
Data Index: 4851379 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9549. Min Range: -2.9549
Max Act: 2.7802. Min Act: -0.1700
Data Index: 3024129 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9549. Min Range: -2.9549
Max Act: 2.7802. Min Act: -0.1700
Data Index: 7940371 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9549. Min Range: -2.9549
Max Act: 2.7802. Min Act: -0.1700
Data Index: 8425305 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9549. Min Range: -2.9549
Max Act: 2.7643. Min Act: -0.1700
Data Index: 6991160 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9549. Min Range: -2.9549
Max Act: 2.7643. Min Act: -0.1700
Data Index: 3024121 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9549. Min Range: -2.9549
Max Act: 2.7643. Min Act: -0.1700
Data Index: 3024136 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9549. Min Range: -2.9549
Max Act: 2.7643. Min Act: -0.1700
Data Index: 1484978 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9549. Min Range: -2.9549
Max Act: 2.7483. Min Act: -0.1700
Data Index: 7776153 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9549. Min Range: -2.9549
Max Act: 2.7483. Min Act: -0.1700
Data Index: 2865095 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9549. Min Range: -2.9549
Max Act: 2.7483. Min Act: -0.1700
Data Index: 2543234 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #19