Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2706 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2269. Min Range: -7.2269
Max Act: 7.2269. Min Act: -0.1700
Data Index: 5442850 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2269. Min Range: -7.2269
Max Act: 7.1957. Min Act: -0.1700
Data Index: 4996681 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2269. Min Range: -7.2269
Max Act: 7.1332. Min Act: -0.1700
Data Index: 1623652 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2269. Min Range: -7.2269
Max Act: 6.9769. Min Act: -0.1700
Data Index: 2717418 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2269. Min Range: -7.2269
Max Act: 6.8832. Min Act: -0.1700
Data Index: 2717420 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2269. Min Range: -7.2269
Max Act: 6.7269. Min Act: -0.1700
Data Index: 5933704 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2269. Min Range: -7.2269
Max Act: 6.6957. Min Act: -0.1700
Data Index: 957009 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2269. Min Range: -7.2269
Max Act: 6.6019. Min Act: -0.1700
Data Index: 8716054 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2269. Min Range: -7.2269
Max Act: 6.5707. Min Act: -0.1700
Data Index: 994133 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2269. Min Range: -7.2269
Max Act: 6.5707. Min Act: -0.1700
Data Index: 7135344 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2269. Min Range: -7.2269
Max Act: 6.5394. Min Act: -0.1700
Data Index: 2013661 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2269. Min Range: -7.2269
Max Act: 6.5394. Min Act: -0.1700
Data Index: 3691989 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2269. Min Range: -7.2269
Max Act: 6.5082. Min Act: -0.1700
Data Index: 6191344 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2269. Min Range: -7.2269
Max Act: 6.5082. Min Act: -0.1700
Data Index: 6906876 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2269. Min Range: -7.2269
Max Act: 6.4769. Min Act: -0.1700
Data Index: 4777765 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2269. Min Range: -7.2269
Max Act: 6.4769. Min Act: -0.1700
Data Index: 6415627 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2269. Min Range: -7.2269
Max Act: 6.4144. Min Act: -0.1700
Data Index: 5911991 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2269. Min Range: -7.2269
Max Act: 6.4457. Min Act: -0.1700
Data Index: 987021 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2269. Min Range: -7.2269
Max Act: 6.4457. Min Act: -0.1700
Data Index: 4292347 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2269. Min Range: -7.2269
Max Act: 6.4457. Min Act: -0.1700
Data Index: 8325454 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #19