Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4542 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6703. Min Range: -4.6703
Max Act: 4.6703. Min Act: -0.1700
Data Index: 3616582 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6703. Min Range: -4.6703
Max Act: 4.6078. Min Act: -0.1700
Data Index: 6439988 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6703. Min Range: -4.6703
Max Act: 4.6078. Min Act: -0.1700
Data Index: 3737282 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6703. Min Range: -4.6703
Max Act: 4.6078. Min Act: -0.1700
Data Index: 6355177 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6703. Min Range: -4.6703
Max Act: 4.6078. Min Act: -0.1700
Data Index: 769524 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6703. Min Range: -4.6703
Max Act: 4.6078. Min Act: -0.1700
Data Index: 4044681 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6703. Min Range: -4.6703
Max Act: 4.5765. Min Act: -0.1700
Data Index: 1960342 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6703. Min Range: -4.6703
Max Act: 4.5765. Min Act: -0.1700
Data Index: 6355171 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6703. Min Range: -4.6703
Max Act: 4.5453. Min Act: -0.1700
Data Index: 8744572 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6703. Min Range: -4.6703
Max Act: 4.5765. Min Act: -0.1700
Data Index: 3684764 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6703. Min Range: -4.6703
Max Act: 4.5453. Min Act: -0.1700
Data Index: 519815 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6703. Min Range: -4.6703
Max Act: 4.5453. Min Act: -0.1700
Data Index: 927152 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6703. Min Range: -4.6703
Max Act: 4.5453. Min Act: -0.1700
Data Index: 8744603 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6703. Min Range: -4.6703
Max Act: 4.5140. Min Act: -0.1700
Data Index: 5221295 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6703. Min Range: -4.6703
Max Act: 4.5453. Min Act: -0.1700
Data Index: 8313895 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6703. Min Range: -4.6703
Max Act: 4.5453. Min Act: -0.1699
Data Index: 6967016 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6703. Min Range: -4.6703
Max Act: 4.5140. Min Act: -0.1700
Data Index: 3401969 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6703. Min Range: -4.6703
Max Act: 4.5140. Min Act: -0.1700
Data Index: 4406057 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6703. Min Range: -4.6703
Max Act: 4.5140. Min Act: -0.1700
Data Index: 273036 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6703. Min Range: -4.6703
Max Act: 4.5140. Min Act: -0.1700
Data Index: 5561552 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #19