Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2296 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4876. Min Range: -6.4876
Max Act: 6.4876. Min Act: -0.1700
Data Index: 2111373 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4876. Min Range: -6.4876
Max Act: 6.4564. Min Act: -0.1700
Data Index: 2489186 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4876. Min Range: -6.4876
Max Act: 6.3001. Min Act: -0.1700
Data Index: 7256331 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4876. Min Range: -6.4876
Max Act: 6.3314. Min Act: -0.1700
Data Index: 2013749 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4876. Min Range: -6.4876
Max Act: 6.2689. Min Act: -0.1700
Data Index: 3207294 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4876. Min Range: -6.4876
Max Act: 6.3001. Min Act: -0.1700
Data Index: 8189686 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4876. Min Range: -6.4876
Max Act: 6.2064. Min Act: -0.1700
Data Index: 6284147 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4876. Min Range: -6.4876
Max Act: 6.2064. Min Act: -0.1700
Data Index: 7575998 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4876. Min Range: -6.4876
Max Act: 6.0814. Min Act: -0.1700
Data Index: 4202870 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4876. Min Range: -6.4876
Max Act: 6.0814. Min Act: -0.1700
Data Index: 617133 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4876. Min Range: -6.4876
Max Act: 6.0501. Min Act: -0.1700
Data Index: 6933028 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4876. Min Range: -6.4876
Max Act: 6.0814. Min Act: -0.1700
Data Index: 20584 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4876. Min Range: -6.4876
Max Act: 6.0189. Min Act: -0.1700
Data Index: 3461880 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4876. Min Range: -6.4876
Max Act: 5.9564. Min Act: -0.1700
Data Index: 6966412 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4876. Min Range: -6.4876
Max Act: 5.9251. Min Act: -0.1700
Data Index: 8555975 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4876. Min Range: -6.4876
Max Act: 5.8939. Min Act: -0.1700
Data Index: 7399095 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4876. Min Range: -6.4876
Max Act: 5.9564. Min Act: -0.1700
Data Index: 5272088 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4876. Min Range: -6.4876
Max Act: 5.8939. Min Act: -0.1700
Data Index: 7034514 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4876. Min Range: -6.4876
Max Act: 5.8626. Min Act: -0.1700
Data Index: 3257104 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4876. Min Range: -6.4876
Max Act: 5.8939. Min Act: -0.1700
Data Index: 5075830 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #19