Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3492 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8967. Min Range: -6.8967
Max Act: 6.8967. Min Act: -0.1700
Data Index: 7376080 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8967. Min Range: -6.8967
Max Act: 6.8655. Min Act: -0.1700
Data Index: 2296700 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8967. Min Range: -6.8967
Max Act: 6.8342. Min Act: -0.1700
Data Index: 8229529 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8967. Min Range: -6.8967
Max Act: 6.8342. Min Act: -0.1700
Data Index: 5327629 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8967. Min Range: -6.8967
Max Act: 6.7717. Min Act: -0.1700
Data Index: 2561446 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8967. Min Range: -6.8967
Max Act: 6.6467. Min Act: -0.1700
Data Index: 5730236 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8967. Min Range: -6.8967
Max Act: 6.6780. Min Act: -0.1700
Data Index: 2746193 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8967. Min Range: -6.8967
Max Act: 6.6155. Min Act: -0.1700
Data Index: 6395307 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8967. Min Range: -6.8967
Max Act: 6.6155. Min Act: -0.1700
Data Index: 2284741 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8967. Min Range: -6.8967
Max Act: 6.6155. Min Act: -0.1700
Data Index: 112029 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8967. Min Range: -6.8967
Max Act: 6.5842. Min Act: -0.1700
Data Index: 6418669 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8967. Min Range: -6.8967
Max Act: 6.5530. Min Act: -0.1700
Data Index: 2296689 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8967. Min Range: -6.8967
Max Act: 6.5842. Min Act: -0.1700
Data Index: 5043122 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8967. Min Range: -6.8967
Max Act: 6.4905. Min Act: -0.1700
Data Index: 226984 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8967. Min Range: -6.8967
Max Act: 6.5217. Min Act: -0.1700
Data Index: 4145137 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8967. Min Range: -6.8967
Max Act: 6.4592. Min Act: -0.1700
Data Index: 2881038 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8967. Min Range: -6.8967
Max Act: 6.4592. Min Act: -0.1700
Data Index: 3045545 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8967. Min Range: -6.8967
Max Act: 6.4280. Min Act: -0.1700
Data Index: 6008878 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8967. Min Range: -6.8967
Max Act: 6.4280. Min Act: -0.1700
Data Index: 4269118 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8967. Min Range: -6.8967
Max Act: 6.3030. Min Act: -0.1700
Data Index: 4926796 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #19