Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1200 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7346. Min Range: -6.7346
Max Act: 6.7346. Min Act: -0.1700
Data Index: 3598820 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7346. Min Range: -6.7346
Max Act: 6.4221. Min Act: -0.1700
Data Index: 1566972 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7346. Min Range: -6.7346
Max Act: 6.4221. Min Act: -0.1700
Data Index: 5692690 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7346. Min Range: -6.7346
Max Act: 6.3908. Min Act: -0.1700
Data Index: 1069379 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7346. Min Range: -6.7346
Max Act: 6.2658. Min Act: -0.1700
Data Index: 3234410 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7346. Min Range: -6.7346
Max Act: 6.2033. Min Act: -0.1700
Data Index: 7869438 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7346. Min Range: -6.7346
Max Act: 6.2346. Min Act: -0.1700
Data Index: 1881679 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7346. Min Range: -6.7346
Max Act: 6.2033. Min Act: -0.1700
Data Index: 271374 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7346. Min Range: -6.7346
Max Act: 6.1408. Min Act: -0.1700
Data Index: 6178173 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7346. Min Range: -6.7346
Max Act: 6.1408. Min Act: -0.1700
Data Index: 2941345 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7346. Min Range: -6.7346
Max Act: 6.1096. Min Act: -0.1700
Data Index: 7086958 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7346. Min Range: -6.7346
Max Act: 6.0471. Min Act: -0.1700
Data Index: 2314518 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7346. Min Range: -6.7346
Max Act: 6.0783. Min Act: -0.1700
Data Index: 8298636 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7346. Min Range: -6.7346
Max Act: 6.0783. Min Act: -0.1700
Data Index: 2323373 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7346. Min Range: -6.7346
Max Act: 6.0471. Min Act: -0.1700
Data Index: 5695418 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7346. Min Range: -6.7346
Max Act: 6.0783. Min Act: -0.1700
Data Index: 4300126 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7346. Min Range: -6.7346
Max Act: 6.0158. Min Act: -0.1700
Data Index: 8189153 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7346. Min Range: -6.7346
Max Act: 6.0158. Min Act: -0.1700
Data Index: 593750 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7346. Min Range: -6.7346
Max Act: 6.0158. Min Act: -0.1700
Data Index: 4202466 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7346. Min Range: -6.7346
Max Act: 6.0158. Min Act: -0.1700
Data Index: 3178311 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #19