Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 386 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7156. Min Range: -7.7156
Max Act: 7.7156. Min Act: -0.1700
Data Index: 1703063 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7156. Min Range: -7.7156
Max Act: 7.6219. Min Act: -0.1700
Data Index: 549214 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7156. Min Range: -7.7156
Max Act: 7.5906. Min Act: -0.1700
Data Index: 5327211 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7156. Min Range: -7.7156
Max Act: 7.5594. Min Act: -0.1700
Data Index: 935103 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7156. Min Range: -7.7156
Max Act: 7.5281. Min Act: -0.1700
Data Index: 8284989 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7156. Min Range: -7.7156
Max Act: 7.4656. Min Act: -0.1700
Data Index: 4184991 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7156. Min Range: -7.7156
Max Act: 7.4969. Min Act: -0.1700
Data Index: 2391954 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7156. Min Range: -7.7156
Max Act: 7.4344. Min Act: -0.1700
Data Index: 1692886 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7156. Min Range: -7.7156
Max Act: 7.4031. Min Act: -0.1700
Data Index: 6380741 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7156. Min Range: -7.7156
Max Act: 7.3406. Min Act: -0.1700
Data Index: 3795882 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7156. Min Range: -7.7156
Max Act: 7.3406. Min Act: -0.1700
Data Index: 3440108 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7156. Min Range: -7.7156
Max Act: 7.3406. Min Act: -0.1700
Data Index: 7956136 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7156. Min Range: -7.7156
Max Act: 7.3094. Min Act: -0.1700
Data Index: 6240914 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7156. Min Range: -7.7156
Max Act: 7.2781. Min Act: -0.1700
Data Index: 7932079 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7156. Min Range: -7.7156
Max Act: 7.2781. Min Act: -0.1700
Data Index: 7342920 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7156. Min Range: -7.7156
Max Act: 7.2469. Min Act: -0.1700
Data Index: 1506873 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7156. Min Range: -7.7156
Max Act: 7.2469. Min Act: -0.1700
Data Index: 8267747 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7156. Min Range: -7.7156
Max Act: 7.2781. Min Act: -0.1700
Data Index: 8193641 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7156. Min Range: -7.7156
Max Act: 7.2469. Min Act: -0.1700
Data Index: 2311263 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7156. Min Range: -7.7156
Max Act: 7.2156. Min Act: -0.1700
Data Index: 8262945 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #19