Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1340 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3310. Min Range: -9.3310
Max Act: 9.3310. Min Act: -0.1700
Data Index: 1775693 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3310. Min Range: -9.3310
Max Act: 9.2685. Min Act: -0.1700
Data Index: 4159126 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3310. Min Range: -9.3310
Max Act: 9.2060. Min Act: -0.1700
Data Index: 5809721 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3310. Min Range: -9.3310
Max Act: 9.1435. Min Act: -0.1700
Data Index: 2417518 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3310. Min Range: -9.3310
Max Act: 9.1435. Min Act: -0.1700
Data Index: 1172875 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3310. Min Range: -9.3310
Max Act: 9.0810. Min Act: -0.1700
Data Index: 1132379 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3310. Min Range: -9.3310
Max Act: 9.0810. Min Act: -0.1700
Data Index: 864857 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3310. Min Range: -9.3310
Max Act: 9.0810. Min Act: -0.1700
Data Index: 1132384 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3310. Min Range: -9.3310
Max Act: 9.0185. Min Act: -0.1700
Data Index: 6792313 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3310. Min Range: -9.3310
Max Act: 9.0185. Min Act: -0.1700
Data Index: 7250881 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3310. Min Range: -9.3310
Max Act: 8.9560. Min Act: -0.1700
Data Index: 1322958 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3310. Min Range: -9.3310
Max Act: 8.8935. Min Act: -0.1700
Data Index: 7732266 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3310. Min Range: -9.3310
Max Act: 8.8935. Min Act: -0.1700
Data Index: 7249718 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3310. Min Range: -9.3310
Max Act: 8.8935. Min Act: -0.1700
Data Index: 7181099 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3310. Min Range: -9.3310
Max Act: 8.8935. Min Act: -0.1700
Data Index: 8380429 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3310. Min Range: -9.3310
Max Act: 8.8935. Min Act: -0.1700
Data Index: 7412709 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3310. Min Range: -9.3310
Max Act: 8.8935. Min Act: -0.1700
Data Index: 7806668 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3310. Min Range: -9.3310
Max Act: 8.8310. Min Act: -0.1700
Data Index: 4887316 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3310. Min Range: -9.3310
Max Act: 8.7685. Min Act: -0.1700
Data Index: 1151247 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3310. Min Range: -9.3310
Max Act: 8.7685. Min Act: -0.1700
Data Index: 7418929 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #19