Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1145 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.4552. Min Range: -7.4552
Max Act: 7.4552. Min Act: -0.1700
Data Index: 4649699 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4552. Min Range: -7.4552
Max Act: 7.1739. Min Act: -0.1700
Data Index: 2523732 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4552. Min Range: -7.4552
Max Act: 7.1427. Min Act: -0.1700
Data Index: 8251696 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4552. Min Range: -7.4552
Max Act: 7.1114. Min Act: -0.1700
Data Index: 514590 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4552. Min Range: -7.4552
Max Act: 7.1114. Min Act: -0.1700
Data Index: 8638629 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4552. Min Range: -7.4552
Max Act: 7.0489. Min Act: -0.1700
Data Index: 1355510 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4552. Min Range: -7.4552
Max Act: 7.0802. Min Act: -0.1700
Data Index: 3465430 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4552. Min Range: -7.4552
Max Act: 7.0802. Min Act: -0.1700
Data Index: 3877466 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4552. Min Range: -7.4552
Max Act: 7.0177. Min Act: -0.1700
Data Index: 469866 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4552. Min Range: -7.4552
Max Act: 6.9864. Min Act: -0.1700
Data Index: 2860410 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4552. Min Range: -7.4552
Max Act: 6.9552. Min Act: -0.1700
Data Index: 952909 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4552. Min Range: -7.4552
Max Act: 6.9864. Min Act: -0.1700
Data Index: 7002377 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4552. Min Range: -7.4552
Max Act: 6.9864. Min Act: -0.1700
Data Index: 5979667 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4552. Min Range: -7.4552
Max Act: 7.0177. Min Act: -0.1700
Data Index: 6847301 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4552. Min Range: -7.4552
Max Act: 6.9239. Min Act: -0.1700
Data Index: 7268302 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4552. Min Range: -7.4552
Max Act: 6.9239. Min Act: -0.1700
Data Index: 4381540 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4552. Min Range: -7.4552
Max Act: 6.8927. Min Act: -0.1700
Data Index: 615798 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4552. Min Range: -7.4552
Max Act: 6.8927. Min Act: -0.1700
Data Index: 3400772 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4552. Min Range: -7.4552
Max Act: 6.8927. Min Act: -0.1700
Data Index: 2610526 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4552. Min Range: -7.4552
Max Act: 6.8927. Min Act: -0.1700
Data Index: 3098959 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #19