Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1328 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6399. Min Range: -5.6399
Max Act: 5.6399. Min Act: -0.1700
Data Index: 89563 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6399. Min Range: -5.6399
Max Act: 5.5774. Min Act: -0.1700
Data Index: 7989299 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6399. Min Range: -5.6399
Max Act: 5.4837. Min Act: -0.1700
Data Index: 3977273 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6399. Min Range: -5.6399
Max Act: 5.5149. Min Act: -0.1700
Data Index: 910884 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6399. Min Range: -5.6399
Max Act: 5.4837. Min Act: -0.1700
Data Index: 2612184 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6399. Min Range: -5.6399
Max Act: 5.4212. Min Act: -0.1700
Data Index: 2955177 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6399. Min Range: -5.6399
Max Act: 5.4212. Min Act: -0.1700
Data Index: 7506850 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6399. Min Range: -5.6399
Max Act: 5.3899. Min Act: -0.1700
Data Index: 4570151 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6399. Min Range: -5.6399
Max Act: 5.3899. Min Act: -0.1700
Data Index: 5033469 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6399. Min Range: -5.6399
Max Act: 5.3274. Min Act: -0.1700
Data Index: 2856309 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6399. Min Range: -5.6399
Max Act: 5.2962. Min Act: -0.1700
Data Index: 6860656 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6399. Min Range: -5.6399
Max Act: 5.3274. Min Act: -0.1700
Data Index: 6334026 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6399. Min Range: -5.6399
Max Act: 5.2962. Min Act: -0.1700
Data Index: 3356563 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6399. Min Range: -5.6399
Max Act: 5.3274. Min Act: -0.1700
Data Index: 3572271 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6399. Min Range: -5.6399
Max Act: 5.3274. Min Act: -0.1700
Data Index: 6318306 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6399. Min Range: -5.6399
Max Act: 5.2962. Min Act: -0.1700
Data Index: 8063352 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6399. Min Range: -5.6399
Max Act: 5.2962. Min Act: -0.1700
Data Index: 8230933 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6399. Min Range: -5.6399
Max Act: 5.3274. Min Act: -0.1700
Data Index: 7695163 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6399. Min Range: -5.6399
Max Act: 5.2962. Min Act: -0.1700
Data Index: 1843924 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6399. Min Range: -5.6399
Max Act: 5.2962. Min Act: -0.1700
Data Index: 4283670 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #19