Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4015 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6276. Min Range: -3.6276
Max Act: 3.6276. Min Act: -0.1700
Data Index: 429676 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6276. Min Range: -3.6276
Max Act: 3.5963. Min Act: -0.1700
Data Index: 8303052 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6276. Min Range: -3.6276
Max Act: 3.5180. Min Act: -0.1700
Data Index: 4183862 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6276. Min Range: -3.6276
Max Act: 3.5023. Min Act: -0.1700
Data Index: 8643055 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6276. Min Range: -3.6276
Max Act: 3.4867. Min Act: -0.1700
Data Index: 5769402 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6276. Min Range: -3.6276
Max Act: 3.4867. Min Act: -0.1700
Data Index: 2624282 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6276. Min Range: -3.6276
Max Act: 3.4397. Min Act: -0.1700
Data Index: 3692927 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6276. Min Range: -3.6276
Max Act: 3.4397. Min Act: -0.1700
Data Index: 2353794 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6276. Min Range: -3.6276
Max Act: 3.4397. Min Act: -0.1700
Data Index: 2928914 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6276. Min Range: -3.6276
Max Act: 3.4240. Min Act: -0.1700
Data Index: 6359604 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6276. Min Range: -3.6276
Max Act: 3.4083. Min Act: -0.1700
Data Index: 2675987 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6276. Min Range: -3.6276
Max Act: 3.4240. Min Act: -0.1700
Data Index: 5135583 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6276. Min Range: -3.6276
Max Act: 3.3926. Min Act: -0.1700
Data Index: 1915699 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6276. Min Range: -3.6276
Max Act: 3.3926. Min Act: -0.1700
Data Index: 5513082 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6276. Min Range: -3.6276
Max Act: 3.3770. Min Act: -0.1700
Data Index: 5285597 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6276. Min Range: -3.6276
Max Act: 3.3926. Min Act: -0.1700
Data Index: 7493677 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6276. Min Range: -3.6276
Max Act: 3.3926. Min Act: -0.1700
Data Index: 7169982 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6276. Min Range: -3.6276
Max Act: 3.3926. Min Act: -0.1700
Data Index: 2931704 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6276. Min Range: -3.6276
Max Act: 3.3770. Min Act: -0.1700
Data Index: 3372129 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6276. Min Range: -3.6276
Max Act: 3.3613. Min Act: -0.1700
Data Index: 1708516 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19