Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3413 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8173. Min Range: -6.8173
Max Act: 6.8173. Min Act: -0.1700
Data Index: 6274336 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8173. Min Range: -6.8173
Max Act: 6.3798. Min Act: -0.1700
Data Index: 1379705 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8173. Min Range: -6.8173
Max Act: 6.3486. Min Act: -0.1700
Data Index: 7966571 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8173. Min Range: -6.8173
Max Act: 6.3486. Min Act: -0.1700
Data Index: 675356 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8173. Min Range: -6.8173
Max Act: 6.2861. Min Act: -0.1700
Data Index: 1980309 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8173. Min Range: -6.8173
Max Act: 6.2861. Min Act: -0.1700
Data Index: 8089106 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8173. Min Range: -6.8173
Max Act: 6.2861. Min Act: -0.1700
Data Index: 4370690 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8173. Min Range: -6.8173
Max Act: 6.2236. Min Act: -0.1700
Data Index: 3124559 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8173. Min Range: -6.8173
Max Act: 6.2236. Min Act: -0.1700
Data Index: 7350730 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8173. Min Range: -6.8173
Max Act: 6.1923. Min Act: -0.1700
Data Index: 2475251 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8173. Min Range: -6.8173
Max Act: 6.1923. Min Act: -0.1700
Data Index: 3808967 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8173. Min Range: -6.8173
Max Act: 6.1923. Min Act: -0.1700
Data Index: 1079060 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8173. Min Range: -6.8173
Max Act: 6.1923. Min Act: -0.1700
Data Index: 3457261 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8173. Min Range: -6.8173
Max Act: 6.1923. Min Act: -0.1700
Data Index: 2593777 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8173. Min Range: -6.8173
Max Act: 6.1923. Min Act: -0.1700
Data Index: 4215026 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8173. Min Range: -6.8173
Max Act: 6.1298. Min Act: -0.1700
Data Index: 7861439 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8173. Min Range: -6.8173
Max Act: 6.1611. Min Act: -0.1700
Data Index: 1855487 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8173. Min Range: -6.8173
Max Act: 6.1611. Min Act: -0.1700
Data Index: 124895 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8173. Min Range: -6.8173
Max Act: 6.1611. Min Act: -0.1700
Data Index: 2679977 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8173. Min Range: -6.8173
Max Act: 6.1611. Min Act: -0.1700
Data Index: 3990249 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #19