Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2198 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8472. Min Range: -6.8472
Max Act: 6.8472. Min Act: -0.1700
Data Index: 2012636 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8472. Min Range: -6.8472
Max Act: 6.8160. Min Act: -0.1700
Data Index: 2141276 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8472. Min Range: -6.8472
Max Act: 6.7222. Min Act: -0.1700
Data Index: 812674 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8472. Min Range: -6.8472
Max Act: 6.5660. Min Act: -0.1700
Data Index: 3151561 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8472. Min Range: -6.8472
Max Act: 6.5660. Min Act: -0.1700
Data Index: 7551523 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8472. Min Range: -6.8472
Max Act: 6.5660. Min Act: -0.1700
Data Index: 1092112 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8472. Min Range: -6.8472
Max Act: 6.5035. Min Act: -0.1700
Data Index: 1598065 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8472. Min Range: -6.8472
Max Act: 6.5035. Min Act: -0.1700
Data Index: 5820998 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8472. Min Range: -6.8472
Max Act: 6.4410. Min Act: -0.1700
Data Index: 2604758 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8472. Min Range: -6.8472
Max Act: 6.4410. Min Act: -0.1700
Data Index: 7733894 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8472. Min Range: -6.8472
Max Act: 6.4410. Min Act: -0.1700
Data Index: 1949131 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8472. Min Range: -6.8472
Max Act: 6.4097. Min Act: -0.1700
Data Index: 1633968 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8472. Min Range: -6.8472
Max Act: 6.4097. Min Act: -0.1700
Data Index: 4642847 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8472. Min Range: -6.8472
Max Act: 6.3472. Min Act: -0.1700
Data Index: 3032280 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8472. Min Range: -6.8472
Max Act: 6.3472. Min Act: -0.1700
Data Index: 4793548 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8472. Min Range: -6.8472
Max Act: 6.3472. Min Act: -0.1700
Data Index: 5821001 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8472. Min Range: -6.8472
Max Act: 6.3472. Min Act: -0.1700
Data Index: 4408021 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8472. Min Range: -6.8472
Max Act: 6.3160. Min Act: -0.1700
Data Index: 5829226 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8472. Min Range: -6.8472
Max Act: 6.3472. Min Act: -0.1700
Data Index: 3219582 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8472. Min Range: -6.8472
Max Act: 6.3160. Min Act: -0.1700
Data Index: 4503985 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #19