Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3532 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 16.8747. Min Range: -16.8747
Max Act: 16.8747. Min Act: -0.1700
Data Index: 7101206 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 16.8747. Min Range: -16.8747
Max Act: 16.7497. Min Act: -0.1691
Data Index: 5425942 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 16.8747. Min Range: -16.8747
Max Act: 16.3747. Min Act: -0.1700
Data Index: 4454128 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 16.8747. Min Range: -16.8747
Max Act: 16.4997. Min Act: -0.1700
Data Index: 5825273 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 16.8747. Min Range: -16.8747
Max Act: 16.4997. Min Act: -0.1700
Data Index: 5951631 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 16.8747. Min Range: -16.8747
Max Act: 16.4997. Min Act: -0.1700
Data Index: 7298610 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 16.8747. Min Range: -16.8747
Max Act: 16.2497. Min Act: -0.1700
Data Index: 5239592 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 16.8747. Min Range: -16.8747
Max Act: 16.3747. Min Act: -0.1699
Data Index: 4229968 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 16.8747. Min Range: -16.8747
Max Act: 16.3747. Min Act: -0.1700
Data Index: 8575330 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 16.8747. Min Range: -16.8747
Max Act: 16.3747. Min Act: -0.1700
Data Index: 3669376 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 16.8747. Min Range: -16.8747
Max Act: 16.3747. Min Act: -0.1700
Data Index: 8208117 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 16.8747. Min Range: -16.8747
Max Act: 16.3747. Min Act: -0.1700
Data Index: 7295050 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 16.8747. Min Range: -16.8747
Max Act: 16.3747. Min Act: -0.1699
Data Index: 3111524 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 16.8747. Min Range: -16.8747
Max Act: 16.3747. Min Act: -0.1699
Data Index: 3092560 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 16.8747. Min Range: -16.8747
Max Act: 16.2497. Min Act: -0.1700
Data Index: 6984759 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 16.8747. Min Range: -16.8747
Max Act: 16.3747. Min Act: -0.1700
Data Index: 6243276 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 16.8747. Min Range: -16.8747
Max Act: 16.3747. Min Act: -0.1691
Data Index: 122299 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 16.8747. Min Range: -16.8747
Max Act: 16.3747. Min Act: -0.1700
Data Index: 559119 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 16.8747. Min Range: -16.8747
Max Act: 16.3747. Min Act: -0.1699
Data Index: 2587528 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 16.8747. Min Range: -16.8747
Max Act: 16.2497. Min Act: -0.1700
Data Index: 4432972 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #19