Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3988 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3397. Min Range: -5.3397
Max Act: 5.3397. Min Act: -0.1700
Data Index: 4842933 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3397. Min Range: -5.3397
Max Act: 5.2460. Min Act: -0.1700
Data Index: 8556478 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3397. Min Range: -5.3397
Max Act: 5.1522. Min Act: -0.1700
Data Index: 5531181 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3397. Min Range: -5.3397
Max Act: 5.1210. Min Act: -0.1700
Data Index: 4126220 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3397. Min Range: -5.3397
Max Act: 5.1210. Min Act: -0.1700
Data Index: 7075722 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3397. Min Range: -5.3397
Max Act: 5.0897. Min Act: -0.1700
Data Index: 91365 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3397. Min Range: -5.3397
Max Act: 5.0897. Min Act: -0.1700
Data Index: 111826 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3397. Min Range: -5.3397
Max Act: 5.0897. Min Act: -0.1700
Data Index: 6758903 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3397. Min Range: -5.3397
Max Act: 5.0897. Min Act: -0.1700
Data Index: 6525045 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3397. Min Range: -5.3397
Max Act: 5.0585. Min Act: -0.1700
Data Index: 1614557 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3397. Min Range: -5.3397
Max Act: 5.0585. Min Act: -0.1700
Data Index: 8027206 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3397. Min Range: -5.3397
Max Act: 5.0585. Min Act: -0.1700
Data Index: 6441942 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3397. Min Range: -5.3397
Max Act: 5.0272. Min Act: -0.1700
Data Index: 4918054 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3397. Min Range: -5.3397
Max Act: 5.0272. Min Act: -0.1700
Data Index: 8695261 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3397. Min Range: -5.3397
Max Act: 5.0272. Min Act: -0.1700
Data Index: 3450199 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3397. Min Range: -5.3397
Max Act: 5.0272. Min Act: -0.1700
Data Index: 2713988 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3397. Min Range: -5.3397
Max Act: 4.9647. Min Act: -0.1700
Data Index: 1407468 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3397. Min Range: -5.3397
Max Act: 4.9960. Min Act: -0.1700
Data Index: 3394372 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3397. Min Range: -5.3397
Max Act: 5.0272. Min Act: -0.1700
Data Index: 5345459 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3397. Min Range: -5.3397
Max Act: 4.9960. Min Act: -0.1700
Data Index: 804536 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #19