Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3606 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0653. Min Range: -9.0653
Max Act: 9.0653. Min Act: -0.1700
Data Index: 7924073 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0653. Min Range: -9.0653
Max Act: 8.4403. Min Act: -0.1700
Data Index: 6330980 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0653. Min Range: -9.0653
Max Act: 8.3778. Min Act: -0.1700
Data Index: 5637105 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0653. Min Range: -9.0653
Max Act: 8.2528. Min Act: -0.1700
Data Index: 3838602 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0653. Min Range: -9.0653
Max Act: 8.1903. Min Act: -0.1700
Data Index: 6083310 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0653. Min Range: -9.0653
Max Act: 8.0965. Min Act: -0.1700
Data Index: 4899193 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0653. Min Range: -9.0653
Max Act: 8.1278. Min Act: -0.1700
Data Index: 4492824 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0653. Min Range: -9.0653
Max Act: 8.0965. Min Act: -0.1700
Data Index: 7027811 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0653. Min Range: -9.0653
Max Act: 8.0340. Min Act: -0.1700
Data Index: 5184248 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0653. Min Range: -9.0653
Max Act: 8.0340. Min Act: -0.1700
Data Index: 7025811 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0653. Min Range: -9.0653
Max Act: 8.0340. Min Act: -0.1700
Data Index: 4373123 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0653. Min Range: -9.0653
Max Act: 8.0340. Min Act: -0.1700
Data Index: 2675342 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0653. Min Range: -9.0653
Max Act: 7.9715. Min Act: -0.1700
Data Index: 3790554 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0653. Min Range: -9.0653
Max Act: 7.9403. Min Act: -0.1700
Data Index: 8435939 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0653. Min Range: -9.0653
Max Act: 7.9403. Min Act: -0.1700
Data Index: 3290702 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0653. Min Range: -9.0653
Max Act: 7.8778. Min Act: -0.1700
Data Index: 4937741 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0653. Min Range: -9.0653
Max Act: 7.9090. Min Act: -0.1700
Data Index: 8783316 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0653. Min Range: -9.0653
Max Act: 7.9090. Min Act: -0.1700
Data Index: 6116725 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0653. Min Range: -9.0653
Max Act: 7.8778. Min Act: -0.1700
Data Index: 2915230 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0653. Min Range: -9.0653
Max Act: 7.8778. Min Act: -0.1700
Data Index: 8526144 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #19