Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1053 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4560. Min Range: -3.4560
Max Act: 3.4560. Min Act: -0.1700
Data Index: 1788388 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4560. Min Range: -3.4560
Max Act: 3.4247. Min Act: -0.1700
Data Index: 7396047 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4560. Min Range: -3.4560
Max Act: 3.3620. Min Act: -0.1700
Data Index: 5192703 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4560. Min Range: -3.4560
Max Act: 3.3777. Min Act: -0.1700
Data Index: 13301 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4560. Min Range: -3.4560
Max Act: 3.3463. Min Act: -0.1700
Data Index: 1043742 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4560. Min Range: -3.4560
Max Act: 3.3306. Min Act: -0.1700
Data Index: 2896101 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4560. Min Range: -3.4560
Max Act: 3.3149. Min Act: -0.1700
Data Index: 8644609 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4560. Min Range: -3.4560
Max Act: 3.2992. Min Act: -0.1700
Data Index: 6615956 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4560. Min Range: -3.4560
Max Act: 3.2992. Min Act: -0.1700
Data Index: 4760712 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4560. Min Range: -3.4560
Max Act: 3.2678. Min Act: -0.1700
Data Index: 6265657 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4560. Min Range: -3.4560
Max Act: 3.2835. Min Act: -0.1700
Data Index: 5964580 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4560. Min Range: -3.4560
Max Act: 3.2835. Min Act: -0.1700
Data Index: 2523410 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4560. Min Range: -3.4560
Max Act: 3.2835. Min Act: -0.1700
Data Index: 7314658 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4560. Min Range: -3.4560
Max Act: 3.2992. Min Act: -0.1700
Data Index: 7159010 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4560. Min Range: -3.4560
Max Act: 3.2521. Min Act: -0.1700
Data Index: 3791017 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4560. Min Range: -3.4560
Max Act: 3.2678. Min Act: -0.1700
Data Index: 1788387 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4560. Min Range: -3.4560
Max Act: 3.2207. Min Act: -0.1700
Data Index: 720616 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4560. Min Range: -3.4560
Max Act: 3.2207. Min Act: -0.1700
Data Index: 267532 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4560. Min Range: -3.4560
Max Act: 3.2521. Min Act: -0.1700
Data Index: 8010677 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4560. Min Range: -3.4560
Max Act: 3.2364. Min Act: -0.1700
Data Index: 5502298 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #19