Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3589 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7354. Min Range: -5.7354
Max Act: 5.7354. Min Act: -0.1700
Data Index: 1009185 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7354. Min Range: -5.7354
Max Act: 5.7354. Min Act: -0.1700
Data Index: 6018515 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7354. Min Range: -5.7354
Max Act: 5.7042. Min Act: -0.1700
Data Index: 3949407 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7354. Min Range: -5.7354
Max Act: 5.6729. Min Act: -0.1700
Data Index: 3203055 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7354. Min Range: -5.7354
Max Act: 5.6417. Min Act: -0.1700
Data Index: 4158728 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7354. Min Range: -5.7354
Max Act: 5.6417. Min Act: -0.1700
Data Index: 4266528 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7354. Min Range: -5.7354
Max Act: 5.5167. Min Act: -0.1700
Data Index: 3988170 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7354. Min Range: -5.7354
Max Act: 5.5167. Min Act: -0.1700
Data Index: 2046217 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7354. Min Range: -5.7354
Max Act: 5.4854. Min Act: -0.1700
Data Index: 1508850 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7354. Min Range: -5.7354
Max Act: 5.5167. Min Act: -0.1700
Data Index: 970306 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7354. Min Range: -5.7354
Max Act: 5.5167. Min Act: -0.1700
Data Index: 8467331 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7354. Min Range: -5.7354
Max Act: 5.4854. Min Act: -0.1700
Data Index: 844594 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7354. Min Range: -5.7354
Max Act: 5.4854. Min Act: -0.1700
Data Index: 7573160 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7354. Min Range: -5.7354
Max Act: 5.4542. Min Act: -0.1700
Data Index: 1251431 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7354. Min Range: -5.7354
Max Act: 5.4542. Min Act: -0.1700
Data Index: 7212352 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7354. Min Range: -5.7354
Max Act: 5.4229. Min Act: -0.1700
Data Index: 3222781 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7354. Min Range: -5.7354
Max Act: 5.4542. Min Act: -0.1700
Data Index: 770198 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7354. Min Range: -5.7354
Max Act: 5.4229. Min Act: -0.1700
Data Index: 2853169 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7354. Min Range: -5.7354
Max Act: 5.4542. Min Act: -0.1700
Data Index: 4167451 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7354. Min Range: -5.7354
Max Act: 5.3917. Min Act: -0.1700
Data Index: 4012304 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #19