Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3437 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8622. Min Range: -8.8622
Max Act: 8.8622. Min Act: -0.1700
Data Index: 3584296 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8622. Min Range: -8.8622
Max Act: 8.3622. Min Act: -0.1700
Data Index: 8201828 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8622. Min Range: -8.8622
Max Act: 8.2997. Min Act: -0.1700
Data Index: 6763184 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8622. Min Range: -8.8622
Max Act: 8.2372. Min Act: -0.1700
Data Index: 4587351 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8622. Min Range: -8.8622
Max Act: 8.1747. Min Act: -0.1700
Data Index: 1911061 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8622. Min Range: -8.8622
Max Act: 8.0497. Min Act: -0.1700
Data Index: 7705148 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8622. Min Range: -8.8622
Max Act: 7.9247. Min Act: -0.1700
Data Index: 4448045 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8622. Min Range: -8.8622
Max Act: 7.9872. Min Act: -0.1700
Data Index: 5614659 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8622. Min Range: -8.8622
Max Act: 7.9247. Min Act: -0.1700
Data Index: 2352752 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8622. Min Range: -8.8622
Max Act: 7.9247. Min Act: -0.1700
Data Index: 8051610 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8622. Min Range: -8.8622
Max Act: 7.9247. Min Act: -0.1700
Data Index: 8594549 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8622. Min Range: -8.8622
Max Act: 7.9247. Min Act: -0.1700
Data Index: 2318653 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8622. Min Range: -8.8622
Max Act: 7.8622. Min Act: -0.1700
Data Index: 7744310 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8622. Min Range: -8.8622
Max Act: 7.8622. Min Act: -0.1700
Data Index: 5034781 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8622. Min Range: -8.8622
Max Act: 7.8622. Min Act: -0.1700
Data Index: 6851819 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8622. Min Range: -8.8622
Max Act: 7.8622. Min Act: -0.1700
Data Index: 4325024 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8622. Min Range: -8.8622
Max Act: 7.7997. Min Act: -0.1700
Data Index: 1309006 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8622. Min Range: -8.8622
Max Act: 7.7997. Min Act: -0.1700
Data Index: 7826033 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8622. Min Range: -8.8622
Max Act: 7.7372. Min Act: -0.1700
Data Index: 5419272 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8622. Min Range: -8.8622
Max Act: 7.7372. Min Act: -0.1700
Data Index: 1751559 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #19