Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4926 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0027. Min Range: -5.0027
Max Act: 5.0027. Min Act: -0.1700
Data Index: 2659706 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0027. Min Range: -5.0027
Max Act: 4.7527. Min Act: -0.1700
Data Index: 1688832 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0027. Min Range: -5.0027
Max Act: 4.7527. Min Act: -0.1700
Data Index: 1359217 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0027. Min Range: -5.0027
Max Act: 4.7214. Min Act: -0.1700
Data Index: 6063589 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0027. Min Range: -5.0027
Max Act: 4.7214. Min Act: -0.1700
Data Index: 3504304 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0027. Min Range: -5.0027
Max Act: 4.6277. Min Act: -0.1700
Data Index: 2811290 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0027. Min Range: -5.0027
Max Act: 4.6277. Min Act: -0.1700
Data Index: 1848718 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0027. Min Range: -5.0027
Max Act: 4.5964. Min Act: -0.1700
Data Index: 5441809 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0027. Min Range: -5.0027
Max Act: 4.5964. Min Act: -0.1700
Data Index: 1483617 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0027. Min Range: -5.0027
Max Act: 4.5652. Min Act: -0.1700
Data Index: 1224814 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0027. Min Range: -5.0027
Max Act: 4.5339. Min Act: -0.1700
Data Index: 6184347 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0027. Min Range: -5.0027
Max Act: 4.5652. Min Act: -0.1700
Data Index: 2228229 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0027. Min Range: -5.0027
Max Act: 4.5652. Min Act: -0.1700
Data Index: 6298553 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0027. Min Range: -5.0027
Max Act: 4.5339. Min Act: -0.1700
Data Index: 774701 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0027. Min Range: -5.0027
Max Act: 4.5339. Min Act: -0.1700
Data Index: 6850557 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0027. Min Range: -5.0027
Max Act: 4.4714. Min Act: -0.1700
Data Index: 249266 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0027. Min Range: -5.0027
Max Act: 4.5027. Min Act: -0.1700
Data Index: 2726694 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0027. Min Range: -5.0027
Max Act: 4.4714. Min Act: -0.1700
Data Index: 5116201 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0027. Min Range: -5.0027
Max Act: 4.4402. Min Act: -0.1700
Data Index: 326477 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0027. Min Range: -5.0027
Max Act: 4.4089. Min Act: -0.1700
Data Index: 4232676 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #19