Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3191 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5419. Min Range: -5.5419
Max Act: 5.5419. Min Act: -0.1700
Data Index: 6153074 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5419. Min Range: -5.5419
Max Act: 5.4482. Min Act: -0.1700
Data Index: 6501314 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5419. Min Range: -5.5419
Max Act: 5.4169. Min Act: -0.1700
Data Index: 1976706 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5419. Min Range: -5.5419
Max Act: 5.3857. Min Act: -0.1700
Data Index: 5488 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5419. Min Range: -5.5419
Max Act: 5.3544. Min Act: -0.1700
Data Index: 5856725 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5419. Min Range: -5.5419
Max Act: 5.3232. Min Act: -0.1700
Data Index: 8162482 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5419. Min Range: -5.5419
Max Act: 5.3232. Min Act: -0.1700
Data Index: 8349534 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5419. Min Range: -5.5419
Max Act: 5.3232. Min Act: -0.1700
Data Index: 5884083 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5419. Min Range: -5.5419
Max Act: 5.2919. Min Act: -0.1700
Data Index: 5995667 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5419. Min Range: -5.5419
Max Act: 5.2919. Min Act: -0.1700
Data Index: 5342638 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5419. Min Range: -5.5419
Max Act: 5.2607. Min Act: -0.1700
Data Index: 4103379 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5419. Min Range: -5.5419
Max Act: 5.2607. Min Act: -0.1700
Data Index: 3308543 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5419. Min Range: -5.5419
Max Act: 5.2607. Min Act: -0.1700
Data Index: 6269936 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5419. Min Range: -5.5419
Max Act: 5.2607. Min Act: -0.1700
Data Index: 3248662 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5419. Min Range: -5.5419
Max Act: 5.2294. Min Act: -0.1700
Data Index: 5623612 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5419. Min Range: -5.5419
Max Act: 5.2294. Min Act: -0.1700
Data Index: 3297409 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5419. Min Range: -5.5419
Max Act: 5.2294. Min Act: -0.1700
Data Index: 1953885 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5419. Min Range: -5.5419
Max Act: 5.1982. Min Act: -0.1700
Data Index: 4789431 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5419. Min Range: -5.5419
Max Act: 5.1982. Min Act: -0.1700
Data Index: 4681871 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5419. Min Range: -5.5419
Max Act: 5.1982. Min Act: -0.1700
Data Index: 6746435 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #19