Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2726 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8295. Min Range: -3.8295
Max Act: 3.8295. Min Act: -0.1700
Data Index: 7996542 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8295. Min Range: -3.8295
Max Act: 3.7201. Min Act: -0.1700
Data Index: 6254083 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8295. Min Range: -3.8295
Max Act: 3.7201. Min Act: -0.1700
Data Index: 6315868 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8295. Min Range: -3.8295
Max Act: 3.7044. Min Act: -0.1700
Data Index: 2609952 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8295. Min Range: -3.8295
Max Act: 3.6418. Min Act: -0.1700
Data Index: 3908825 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8295. Min Range: -3.8295
Max Act: 3.6418. Min Act: -0.1700
Data Index: 8646400 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8295. Min Range: -3.8295
Max Act: 3.6262. Min Act: -0.1700
Data Index: 2350063 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8295. Min Range: -3.8295
Max Act: 3.6105. Min Act: -0.1700
Data Index: 1986821 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8295. Min Range: -3.8295
Max Act: 3.5949. Min Act: -0.1700
Data Index: 6861630 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8295. Min Range: -3.8295
Max Act: 3.5636. Min Act: -0.1700
Data Index: 1843677 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8295. Min Range: -3.8295
Max Act: 3.5949. Min Act: -0.1700
Data Index: 2639907 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8295. Min Range: -3.8295
Max Act: 3.5792. Min Act: -0.1700
Data Index: 4300555 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8295. Min Range: -3.8295
Max Act: 3.5479. Min Act: -0.1700
Data Index: 4755462 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8295. Min Range: -3.8295
Max Act: 3.5636. Min Act: -0.1700
Data Index: 2158092 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8295. Min Range: -3.8295
Max Act: 3.5636. Min Act: -0.1700
Data Index: 3562877 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8295. Min Range: -3.8295
Max Act: 3.5636. Min Act: -0.1700
Data Index: 5569879 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8295. Min Range: -3.8295
Max Act: 3.5323. Min Act: -0.1700
Data Index: 8771453 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8295. Min Range: -3.8295
Max Act: 3.5323. Min Act: -0.1700
Data Index: 1127924 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8295. Min Range: -3.8295
Max Act: 3.5479. Min Act: -0.1700
Data Index: 5955991 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8295. Min Range: -3.8295
Max Act: 3.5166. Min Act: -0.1700
Data Index: 2499822 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #19