Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2785 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4469. Min Range: -5.4469
Max Act: 5.4469. Min Act: -0.1700
Data Index: 8077232 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4469. Min Range: -5.4469
Max Act: 5.4469. Min Act: -0.1700
Data Index: 2283779 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4469. Min Range: -5.4469
Max Act: 5.4156. Min Act: -0.1700
Data Index: 8095685 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4469. Min Range: -5.4469
Max Act: 5.3531. Min Act: -0.1700
Data Index: 8408221 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4469. Min Range: -5.4469
Max Act: 5.3219. Min Act: -0.1700
Data Index: 8139612 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4469. Min Range: -5.4469
Max Act: 5.2906. Min Act: -0.1700
Data Index: 3186326 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4469. Min Range: -5.4469
Max Act: 5.2906. Min Act: -0.1700
Data Index: 8300704 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4469. Min Range: -5.4469
Max Act: 5.2281. Min Act: -0.1700
Data Index: 8157500 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4469. Min Range: -5.4469
Max Act: 5.2594. Min Act: -0.1700
Data Index: 3137709 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4469. Min Range: -5.4469
Max Act: 5.2281. Min Act: -0.1700
Data Index: 7180695 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4469. Min Range: -5.4469
Max Act: 5.1969. Min Act: -0.1700
Data Index: 8536377 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4469. Min Range: -5.4469
Max Act: 5.1969. Min Act: -0.1700
Data Index: 2282293 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4469. Min Range: -5.4469
Max Act: 5.1969. Min Act: -0.1700
Data Index: 4380741 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4469. Min Range: -5.4469
Max Act: 5.1656. Min Act: -0.1700
Data Index: 5093313 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4469. Min Range: -5.4469
Max Act: 5.1656. Min Act: -0.1700
Data Index: 6319437 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4469. Min Range: -5.4469
Max Act: 5.1656. Min Act: -0.1700
Data Index: 4099953 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4469. Min Range: -5.4469
Max Act: 5.1656. Min Act: -0.1700
Data Index: 446937 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4469. Min Range: -5.4469
Max Act: 5.1656. Min Act: -0.1700
Data Index: 1664689 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4469. Min Range: -5.4469
Max Act: 5.1344. Min Act: -0.1700
Data Index: 8346286 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4469. Min Range: -5.4469
Max Act: 5.1344. Min Act: -0.1700
Data Index: 3019710 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #19