Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3253 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6369. Min Range: -5.6369
Max Act: 5.6369. Min Act: -0.1700
Data Index: 6049897 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6369. Min Range: -5.6369
Max Act: 5.4181. Min Act: -0.1700
Data Index: 6368076 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6369. Min Range: -5.6369
Max Act: 5.2931. Min Act: -0.1700
Data Index: 6553268 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6369. Min Range: -5.6369
Max Act: 5.2931. Min Act: -0.1700
Data Index: 2568335 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6369. Min Range: -5.6369
Max Act: 5.2931. Min Act: -0.1700
Data Index: 6364282 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6369. Min Range: -5.6369
Max Act: 5.2619. Min Act: -0.1700
Data Index: 1377633 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6369. Min Range: -5.6369
Max Act: 5.1994. Min Act: -0.1700
Data Index: 680964 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6369. Min Range: -5.6369
Max Act: 5.1681. Min Act: -0.1700
Data Index: 3802148 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6369. Min Range: -5.6369
Max Act: 5.1369. Min Act: -0.1700
Data Index: 8269039 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6369. Min Range: -5.6369
Max Act: 5.1369. Min Act: -0.1700
Data Index: 5104466 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6369. Min Range: -5.6369
Max Act: 5.1681. Min Act: -0.1700
Data Index: 2920 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6369. Min Range: -5.6369
Max Act: 5.1369. Min Act: -0.1700
Data Index: 7168178 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6369. Min Range: -5.6369
Max Act: 5.1056. Min Act: -0.1700
Data Index: 4511575 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6369. Min Range: -5.6369
Max Act: 5.1056. Min Act: -0.1700
Data Index: 1074061 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6369. Min Range: -5.6369
Max Act: 5.0744. Min Act: -0.1700
Data Index: 3790737 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6369. Min Range: -5.6369
Max Act: 5.0744. Min Act: -0.1700
Data Index: 8376984 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6369. Min Range: -5.6369
Max Act: 5.0119. Min Act: -0.1700
Data Index: 5692212 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6369. Min Range: -5.6369
Max Act: 5.0119. Min Act: -0.1700
Data Index: 6290192 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6369. Min Range: -5.6369
Max Act: 5.0119. Min Act: -0.1700
Data Index: 295844 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6369. Min Range: -5.6369
Max Act: 5.0119. Min Act: -0.1700
Data Index: 898945 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19