Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3412 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3310. Min Range: -6.3310
Max Act: 6.3310. Min Act: -0.1700
Data Index: 6083629 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3310. Min Range: -6.3310
Max Act: 6.2685. Min Act: -0.1700
Data Index: 2229079 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3310. Min Range: -6.3310
Max Act: 6.1435. Min Act: -0.1700
Data Index: 915560 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3310. Min Range: -6.3310
Max Act: 6.1123. Min Act: -0.1700
Data Index: 3323184 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3310. Min Range: -6.3310
Max Act: 6.1123. Min Act: -0.1700
Data Index: 5594143 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3310. Min Range: -6.3310
Max Act: 6.0810. Min Act: -0.1700
Data Index: 1972344 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3310. Min Range: -6.3310
Max Act: 6.0185. Min Act: -0.1700
Data Index: 6373314 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3310. Min Range: -6.3310
Max Act: 6.0185. Min Act: -0.1700
Data Index: 1857920 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3310. Min Range: -6.3310
Max Act: 6.0185. Min Act: -0.1700
Data Index: 2276211 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3310. Min Range: -6.3310
Max Act: 6.0185. Min Act: -0.1700
Data Index: 395970 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3310. Min Range: -6.3310
Max Act: 5.9873. Min Act: -0.1700
Data Index: 572001 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3310. Min Range: -6.3310
Max Act: 5.9873. Min Act: -0.1700
Data Index: 380795 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3310. Min Range: -6.3310
Max Act: 5.9560. Min Act: -0.1700
Data Index: 8260311 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3310. Min Range: -6.3310
Max Act: 5.9248. Min Act: -0.1700
Data Index: 580208 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3310. Min Range: -6.3310
Max Act: 5.9248. Min Act: -0.1700
Data Index: 1801170 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3310. Min Range: -6.3310
Max Act: 5.8935. Min Act: -0.1700
Data Index: 3245675 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3310. Min Range: -6.3310
Max Act: 5.8935. Min Act: -0.1700
Data Index: 4193183 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3310. Min Range: -6.3310
Max Act: 5.8623. Min Act: -0.1700
Data Index: 2169653 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3310. Min Range: -6.3310
Max Act: 5.8623. Min Act: -0.1700
Data Index: 4057625 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3310. Min Range: -6.3310
Max Act: 5.8623. Min Act: -0.1700
Data Index: 437860 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #19