Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3435 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2288. Min Range: -4.2288
Max Act: 4.2288. Min Act: -0.1700
Data Index: 5076526 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2288. Min Range: -4.2288
Max Act: 4.2288. Min Act: -0.1700
Data Index: 5388051 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2288. Min Range: -4.2288
Max Act: 4.0413. Min Act: -0.1700
Data Index: 2257368 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2288. Min Range: -4.2288
Max Act: 4.0100. Min Act: -0.1700
Data Index: 1936482 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2288. Min Range: -4.2288
Max Act: 3.9787. Min Act: -0.1700
Data Index: 8820745 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2288. Min Range: -4.2288
Max Act: 3.9787. Min Act: -0.1700
Data Index: 6648923 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2288. Min Range: -4.2288
Max Act: 3.9787. Min Act: -0.1700
Data Index: 4210190 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2288. Min Range: -4.2288
Max Act: 3.9787. Min Act: -0.1700
Data Index: 6330003 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2288. Min Range: -4.2288
Max Act: 3.9787. Min Act: -0.1700
Data Index: 7438543 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2288. Min Range: -4.2288
Max Act: 3.9787. Min Act: -0.1700
Data Index: 4987169 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2288. Min Range: -4.2288
Max Act: 3.9162. Min Act: -0.1700
Data Index: 994230 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2288. Min Range: -4.2288
Max Act: 3.9475. Min Act: -0.1700
Data Index: 8302139 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2288. Min Range: -4.2288
Max Act: 3.9475. Min Act: -0.1700
Data Index: 4967479 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2288. Min Range: -4.2288
Max Act: 3.9787. Min Act: -0.1700
Data Index: 695652 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2288. Min Range: -4.2288
Max Act: 3.9162. Min Act: -0.1700
Data Index: 7225456 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2288. Min Range: -4.2288
Max Act: 3.8849. Min Act: -0.1700
Data Index: 1473014 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2288. Min Range: -4.2288
Max Act: 3.9162. Min Act: -0.1700
Data Index: 5783317 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2288. Min Range: -4.2288
Max Act: 3.9162. Min Act: -0.1700
Data Index: 3973693 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2288. Min Range: -4.2288
Max Act: 3.8849. Min Act: -0.1700
Data Index: 4309630 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2288. Min Range: -4.2288
Max Act: 3.8849. Min Act: -0.1700
Data Index: 1765890 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #19