Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1111 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.8224. Min Range: -1.8224
Max Act: 1.8224. Min Act: -0.1700
Data Index: 5100809 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8224. Min Range: -1.8224
Max Act: 1.8224. Min Act: -0.1700
Data Index: 2595998 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8224. Min Range: -1.8224
Max Act: 1.8138. Min Act: -0.1700
Data Index: 8455668 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8224. Min Range: -1.8224
Max Act: 1.8224. Min Act: -0.1700
Data Index: 7888333 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8224. Min Range: -1.8224
Max Act: 1.7966. Min Act: -0.1700
Data Index: 310637 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8224. Min Range: -1.8224
Max Act: 1.8052. Min Act: -0.1699
Data Index: 2726201 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8224. Min Range: -1.8224
Max Act: 1.7708. Min Act: -0.1698
Data Index: 2152301 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8224. Min Range: -1.8224
Max Act: 1.7880. Min Act: -0.1700
Data Index: 7923736 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8224. Min Range: -1.8224
Max Act: 1.7708. Min Act: -0.1700
Data Index: 937080 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8224. Min Range: -1.8224
Max Act: 1.7535. Min Act: -0.1700
Data Index: 2549407 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8224. Min Range: -1.8224
Max Act: 1.7449. Min Act: -0.1700
Data Index: 8105399 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8224. Min Range: -1.8224
Max Act: 1.7449. Min Act: -0.1700
Data Index: 715579 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8224. Min Range: -1.8224
Max Act: 1.7276. Min Act: -0.1700
Data Index: 5980830 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8224. Min Range: -1.8224
Max Act: 1.7362. Min Act: -0.1700
Data Index: 1392742 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8224. Min Range: -1.8224
Max Act: 1.7362. Min Act: -0.1700
Data Index: 1831790 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8224. Min Range: -1.8224
Max Act: 1.7276. Min Act: -0.1700
Data Index: 7840356 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8224. Min Range: -1.8224
Max Act: 1.7189. Min Act: -0.1700
Data Index: 1647813 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8224. Min Range: -1.8224
Max Act: 1.7103. Min Act: -0.1700
Data Index: 1274270 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8224. Min Range: -1.8224
Max Act: 1.7189. Min Act: -0.1700
Data Index: 1095875 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8224. Min Range: -1.8224
Max Act: 1.7189. Min Act: -0.1700
Data Index: 4263904 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #19