Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2853 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6075. Min Range: -4.6075
Max Act: 4.6075. Min Act: -0.1700
Data Index: 7252296 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6075. Min Range: -4.6075
Max Act: 4.4513. Min Act: -0.1700
Data Index: 1452185 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6075. Min Range: -4.6075
Max Act: 4.4200. Min Act: -0.1700
Data Index: 4249205 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6075. Min Range: -4.6075
Max Act: 4.4200. Min Act: -0.1700
Data Index: 6996214 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6075. Min Range: -4.6075
Max Act: 4.3888. Min Act: -0.1700
Data Index: 421001 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6075. Min Range: -4.6075
Max Act: 4.4200. Min Act: -0.1700
Data Index: 8700238 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6075. Min Range: -4.6075
Max Act: 4.3263. Min Act: -0.1700
Data Index: 5524486 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6075. Min Range: -4.6075
Max Act: 4.3575. Min Act: -0.1700
Data Index: 2815614 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6075. Min Range: -4.6075
Max Act: 4.3888. Min Act: -0.1700
Data Index: 7298897 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6075. Min Range: -4.6075
Max Act: 4.3263. Min Act: -0.1700
Data Index: 7474582 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6075. Min Range: -4.6075
Max Act: 4.2950. Min Act: -0.1700
Data Index: 2791428 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6075. Min Range: -4.6075
Max Act: 4.2638. Min Act: -0.1700
Data Index: 8178210 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6075. Min Range: -4.6075
Max Act: 4.2638. Min Act: -0.1700
Data Index: 1033579 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6075. Min Range: -4.6075
Max Act: 4.2950. Min Act: -0.1700
Data Index: 6417289 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6075. Min Range: -4.6075
Max Act: 4.2950. Min Act: -0.1700
Data Index: 4429232 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6075. Min Range: -4.6075
Max Act: 4.2950. Min Act: -0.1700
Data Index: 1166262 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6075. Min Range: -4.6075
Max Act: 4.2638. Min Act: -0.1700
Data Index: 1202051 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6075. Min Range: -4.6075
Max Act: 4.2638. Min Act: -0.1700
Data Index: 1909210 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6075. Min Range: -4.6075
Max Act: 4.2325. Min Act: -0.1700
Data Index: 1477103 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6075. Min Range: -4.6075
Max Act: 4.2950. Min Act: -0.1700
Data Index: 6883700 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #19