Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2248 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3101. Min Range: -3.3101
Max Act: 3.3101. Min Act: -0.1700
Data Index: 1279449 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3101. Min Range: -3.3101
Max Act: 3.2944. Min Act: -0.1700
Data Index: 163367 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3101. Min Range: -3.3101
Max Act: 3.2944. Min Act: -0.1700
Data Index: 6007638 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3101. Min Range: -3.3101
Max Act: 3.2787. Min Act: -0.1700
Data Index: 4867139 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3101. Min Range: -3.3101
Max Act: 3.2630. Min Act: -0.1700
Data Index: 113939 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3101. Min Range: -3.3101
Max Act: 3.2630. Min Act: -0.1700
Data Index: 6278197 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3101. Min Range: -3.3101
Max Act: 3.2316. Min Act: -0.1700
Data Index: 8365553 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3101. Min Range: -3.3101
Max Act: 3.2158. Min Act: -0.1700
Data Index: 7139629 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3101. Min Range: -3.3101
Max Act: 3.1844. Min Act: -0.1700
Data Index: 5579718 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3101. Min Range: -3.3101
Max Act: 3.1529. Min Act: -0.1700
Data Index: 8665685 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3101. Min Range: -3.3101
Max Act: 3.1687. Min Act: -0.1700
Data Index: 2483481 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3101. Min Range: -3.3101
Max Act: 3.1844. Min Act: -0.1700
Data Index: 287667 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3101. Min Range: -3.3101
Max Act: 3.1687. Min Act: -0.1700
Data Index: 5896991 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3101. Min Range: -3.3101
Max Act: 3.1687. Min Act: -0.1700
Data Index: 2615986 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3101. Min Range: -3.3101
Max Act: 3.1687. Min Act: -0.1700
Data Index: 3176103 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3101. Min Range: -3.3101
Max Act: 3.1687. Min Act: -0.1700
Data Index: 6259891 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3101. Min Range: -3.3101
Max Act: 3.1844. Min Act: -0.1700
Data Index: 4216461 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3101. Min Range: -3.3101
Max Act: 3.1844. Min Act: -0.1700
Data Index: 6666575 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3101. Min Range: -3.3101
Max Act: 3.1372. Min Act: -0.1700
Data Index: 6164875 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3101. Min Range: -3.3101
Max Act: 3.1372. Min Act: -0.1700
Data Index: 3993929 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #19