Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2775 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9710. Min Range: -5.9710
Max Act: 5.9710. Min Act: -0.1700
Data Index: 2563678 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9710. Min Range: -5.9710
Max Act: 5.9085. Min Act: -0.1700
Data Index: 4931271 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9710. Min Range: -5.9710
Max Act: 5.7210. Min Act: -0.1700
Data Index: 1403545 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9710. Min Range: -5.9710
Max Act: 5.6897. Min Act: -0.1700
Data Index: 2899376 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9710. Min Range: -5.9710
Max Act: 5.6897. Min Act: -0.1700
Data Index: 2329352 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9710. Min Range: -5.9710
Max Act: 5.6897. Min Act: -0.1700
Data Index: 3906992 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9710. Min Range: -5.9710
Max Act: 5.6585. Min Act: -0.1700
Data Index: 1303642 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9710. Min Range: -5.9710
Max Act: 5.6585. Min Act: -0.1700
Data Index: 3769784 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9710. Min Range: -5.9710
Max Act: 5.5960. Min Act: -0.1700
Data Index: 2797699 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9710. Min Range: -5.9710
Max Act: 5.5960. Min Act: -0.1700
Data Index: 5535990 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9710. Min Range: -5.9710
Max Act: 5.5960. Min Act: -0.1700
Data Index: 1385937 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9710. Min Range: -5.9710
Max Act: 5.5960. Min Act: -0.1700
Data Index: 8358466 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9710. Min Range: -5.9710
Max Act: 5.5335. Min Act: -0.1700
Data Index: 2465427 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9710. Min Range: -5.9710
Max Act: 5.5335. Min Act: -0.1700
Data Index: 4311908 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9710. Min Range: -5.9710
Max Act: 5.5335. Min Act: -0.1700
Data Index: 870390 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9710. Min Range: -5.9710
Max Act: 5.5335. Min Act: -0.1700
Data Index: 1621233 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9710. Min Range: -5.9710
Max Act: 5.5022. Min Act: -0.1700
Data Index: 4709966 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9710. Min Range: -5.9710
Max Act: 5.5022. Min Act: -0.1700
Data Index: 5076470 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9710. Min Range: -5.9710
Max Act: 5.5022. Min Act: -0.1700
Data Index: 8498103 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9710. Min Range: -5.9710
Max Act: 5.5022. Min Act: -0.1700
Data Index: 6167121 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #19