Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3210 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7359. Min Range: -7.7359
Max Act: 7.7359. Min Act: -0.1700
Data Index: 7581770 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7359. Min Range: -7.7359
Max Act: 7.2984. Min Act: -0.1700
Data Index: 1905762 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7359. Min Range: -7.7359
Max Act: 7.2359. Min Act: -0.1700
Data Index: 2340933 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7359. Min Range: -7.7359
Max Act: 7.1421. Min Act: -0.1700
Data Index: 3976609 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7359. Min Range: -7.7359
Max Act: 7.0796. Min Act: -0.1700
Data Index: 1909332 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7359. Min Range: -7.7359
Max Act: 7.0796. Min Act: -0.1700
Data Index: 6678589 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7359. Min Range: -7.7359
Max Act: 7.1109. Min Act: -0.1700
Data Index: 898531 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7359. Min Range: -7.7359
Max Act: 7.0484. Min Act: -0.1700
Data Index: 5359904 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7359. Min Range: -7.7359
Max Act: 7.0484. Min Act: -0.1700
Data Index: 1648785 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7359. Min Range: -7.7359
Max Act: 6.9859. Min Act: -0.1700
Data Index: 4742033 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7359. Min Range: -7.7359
Max Act: 6.9859. Min Act: -0.1700
Data Index: 6465170 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7359. Min Range: -7.7359
Max Act: 6.9546. Min Act: -0.1700
Data Index: 2966160 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7359. Min Range: -7.7359
Max Act: 6.8921. Min Act: -0.1700
Data Index: 2293554 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7359. Min Range: -7.7359
Max Act: 6.8921. Min Act: -0.1700
Data Index: 4429814 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7359. Min Range: -7.7359
Max Act: 6.8609. Min Act: -0.1700
Data Index: 5642653 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7359. Min Range: -7.7359
Max Act: 6.7984. Min Act: -0.1700
Data Index: 7435232 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7359. Min Range: -7.7359
Max Act: 6.8296. Min Act: -0.1700
Data Index: 8152025 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7359. Min Range: -7.7359
Max Act: 6.7671. Min Act: -0.1700
Data Index: 2060679 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7359. Min Range: -7.7359
Max Act: 6.7359. Min Act: -0.1700
Data Index: 3653435 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7359. Min Range: -7.7359
Max Act: 6.7046. Min Act: -0.1700
Data Index: 4016970 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #19