Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1161 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7929. Min Range: -7.7929
Max Act: 7.7929. Min Act: -0.1700
Data Index: 4957756 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7929. Min Range: -7.7929
Max Act: 7.6991. Min Act: -0.1700
Data Index: 4921383 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7929. Min Range: -7.7929
Max Act: 7.4804. Min Act: -0.1700
Data Index: 3914570 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7929. Min Range: -7.7929
Max Act: 7.4491. Min Act: -0.1700
Data Index: 2154172 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7929. Min Range: -7.7929
Max Act: 7.3866. Min Act: -0.1700
Data Index: 8575093 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7929. Min Range: -7.7929
Max Act: 7.3866. Min Act: -0.1700
Data Index: 1344718 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7929. Min Range: -7.7929
Max Act: 7.3241. Min Act: -0.1700
Data Index: 8597492 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7929. Min Range: -7.7929
Max Act: 7.2616. Min Act: -0.1700
Data Index: 868327 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7929. Min Range: -7.7929
Max Act: 7.2304. Min Act: -0.1700
Data Index: 7079781 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7929. Min Range: -7.7929
Max Act: 7.2304. Min Act: -0.1700
Data Index: 1404387 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7929. Min Range: -7.7929
Max Act: 7.1991. Min Act: -0.1700
Data Index: 4945613 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7929. Min Range: -7.7929
Max Act: 7.1679. Min Act: -0.1700
Data Index: 4803331 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7929. Min Range: -7.7929
Max Act: 7.1679. Min Act: -0.1700
Data Index: 8681849 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7929. Min Range: -7.7929
Max Act: 7.1366. Min Act: -0.1700
Data Index: 773890 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7929. Min Range: -7.7929
Max Act: 7.1679. Min Act: -0.1700
Data Index: 4514636 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7929. Min Range: -7.7929
Max Act: 7.1679. Min Act: -0.1700
Data Index: 6931786 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7929. Min Range: -7.7929
Max Act: 7.1366. Min Act: -0.1700
Data Index: 5599034 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7929. Min Range: -7.7929
Max Act: 7.1366. Min Act: -0.1700
Data Index: 6802129 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7929. Min Range: -7.7929
Max Act: 7.1054. Min Act: -0.1700
Data Index: 7925357 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7929. Min Range: -7.7929
Max Act: 7.1054. Min Act: -0.1700
Data Index: 7810216 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #19