Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 2520 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 8.1415. Min Range: -8.1415
Max Act: 8.0165. Min Act: -0.1700
Data Index: 6685127 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1415. Min Range: -8.1415
Max Act: 6.3915. Min Act: -0.1700
Data Index: 5668879 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1415. Min Range: -8.1415
Max Act: 6.3915. Min Act: -0.1695
Data Index: 3692262 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1415. Min Range: -8.1415
Max Act: 5.9853. Min Act: -0.1700
Data Index: 879253 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1415. Min Range: -8.1415
Max Act: 8.1415. Min Act: -0.1700
Data Index: 6685128 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1415. Min Range: -8.1415
Max Act: 6.2978. Min Act: -0.1700
Data Index: 4026176 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1415. Min Range: -8.1415
Max Act: 6.2353. Min Act: -0.1700
Data Index: 4467379 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1415. Min Range: -8.1415
Max Act: 6.2353. Min Act: -0.1700
Data Index: 7422269 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1415. Min Range: -8.1415
Max Act: 6.2040. Min Act: -0.1700
Data Index: 7731901 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1415. Min Range: -8.1415
Max Act: 6.2353. Min Act: -0.1699
Data Index: 7681677 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1415. Min Range: -8.1415
Max Act: 6.2978. Min Act: -0.1700
Data Index: 4538597 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1415. Min Range: -8.1415
Max Act: 6.1415. Min Act: -0.1700
Data Index: 3862650 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1415. Min Range: -8.1415
Max Act: 6.1415. Min Act: -0.1700
Data Index: 8324314 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1415. Min Range: -8.1415
Max Act: 6.0165. Min Act: -0.1700
Data Index: 3966913 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1415. Min Range: -8.1415
Max Act: 6.0790. Min Act: -0.1700
Data Index: 6080969 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1415. Min Range: -8.1415
Max Act: 6.0478. Min Act: -0.1700
Data Index: 4355796 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1415. Min Range: -8.1415
Max Act: 6.1103. Min Act: -0.1700
Data Index: 190431 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1415. Min Range: -8.1415
Max Act: 5.9540. Min Act: -0.1697
Data Index: 190422 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1415. Min Range: -8.1415
Max Act: 5.9540. Min Act: -0.1700
Data Index: 1391703 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1415. Min Range: -8.1415
Max Act: 6.0165. Min Act: -0.1700
Data Index: 6040337 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #19