Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 384 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0605. Min Range: -6.0605
Max Act: 6.0293. Min Act: -0.1700
Data Index: 3470977 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0605. Min Range: -6.0605
Max Act: 6.0605. Min Act: -0.1700
Data Index: 6724731 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0605. Min Range: -6.0605
Max Act: 5.9668. Min Act: -0.1700
Data Index: 7541292 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0605. Min Range: -6.0605
Max Act: 5.8418. Min Act: -0.1700
Data Index: 4654811 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0605. Min Range: -6.0605
Max Act: 5.8418. Min Act: -0.1700
Data Index: 750354 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0605. Min Range: -6.0605
Max Act: 5.7793. Min Act: -0.1700
Data Index: 1374754 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0605. Min Range: -6.0605
Max Act: 5.8105. Min Act: -0.1700
Data Index: 5352200 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0605. Min Range: -6.0605
Max Act: 5.8105. Min Act: -0.1700
Data Index: 5319838 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0605. Min Range: -6.0605
Max Act: 5.7168. Min Act: -0.1700
Data Index: 6884288 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0605. Min Range: -6.0605
Max Act: 5.7168. Min Act: -0.1700
Data Index: 1552649 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0605. Min Range: -6.0605
Max Act: 5.7168. Min Act: -0.1700
Data Index: 7153519 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0605. Min Range: -6.0605
Max Act: 5.6855. Min Act: -0.1700
Data Index: 4450289 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0605. Min Range: -6.0605
Max Act: 5.6855. Min Act: -0.1700
Data Index: 7747561 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0605. Min Range: -6.0605
Max Act: 5.6855. Min Act: -0.1700
Data Index: 7811745 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0605. Min Range: -6.0605
Max Act: 5.6855. Min Act: -0.1700
Data Index: 4395813 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0605. Min Range: -6.0605
Max Act: 5.6543. Min Act: -0.1700
Data Index: 1772810 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0605. Min Range: -6.0605
Max Act: 5.6543. Min Act: -0.1700
Data Index: 4290327 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0605. Min Range: -6.0605
Max Act: 5.6230. Min Act: -0.1700
Data Index: 6220718 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0605. Min Range: -6.0605
Max Act: 5.5918. Min Act: -0.1700
Data Index: 425459 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0605. Min Range: -6.0605
Max Act: 5.6230. Min Act: -0.1700
Data Index: 6675908 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #19