Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5823 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7522. Min Range: -6.7522
Max Act: 6.7522. Min Act: -0.1700
Data Index: 4501157 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7522. Min Range: -6.7522
Max Act: 6.3772. Min Act: -0.1700
Data Index: 3220809 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7522. Min Range: -6.7522
Max Act: 6.3772. Min Act: -0.1700
Data Index: 5989868 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7522. Min Range: -6.7522
Max Act: 6.1897. Min Act: -0.1700
Data Index: 2357414 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7522. Min Range: -6.7522
Max Act: 6.0960. Min Act: -0.1700
Data Index: 1407834 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7522. Min Range: -6.7522
Max Act: 6.0335. Min Act: -0.1700
Data Index: 7152680 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7522. Min Range: -6.7522
Max Act: 5.9397. Min Act: -0.1700
Data Index: 2465817 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7522. Min Range: -6.7522
Max Act: 5.9085. Min Act: -0.1700
Data Index: 3343201 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7522. Min Range: -6.7522
Max Act: 5.9085. Min Act: -0.1700
Data Index: 6204800 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7522. Min Range: -6.7522
Max Act: 5.8460. Min Act: -0.1700
Data Index: 3242025 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7522. Min Range: -6.7522
Max Act: 5.8772. Min Act: -0.1700
Data Index: 3444966 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7522. Min Range: -6.7522
Max Act: 5.8147. Min Act: -0.1700
Data Index: 6013446 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7522. Min Range: -6.7522
Max Act: 5.8460. Min Act: -0.1700
Data Index: 5943240 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7522. Min Range: -6.7522
Max Act: 5.8147. Min Act: -0.1700
Data Index: 7865613 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7522. Min Range: -6.7522
Max Act: 5.8147. Min Act: -0.1700
Data Index: 3493509 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7522. Min Range: -6.7522
Max Act: 5.8147. Min Act: -0.1700
Data Index: 2477154 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7522. Min Range: -6.7522
Max Act: 5.7835. Min Act: -0.1700
Data Index: 7901188 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7522. Min Range: -6.7522
Max Act: 5.7835. Min Act: -0.1700
Data Index: 4160682 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7522. Min Range: -6.7522
Max Act: 5.7522. Min Act: -0.1700
Data Index: 1939563 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7522. Min Range: -6.7522
Max Act: 5.7210. Min Act: -0.1700
Data Index: 3637988 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #19