Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2702 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7461. Min Range: -6.7461
Max Act: 6.7461. Min Act: -0.1700
Data Index: 2556433 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7461. Min Range: -6.7461
Max Act: 6.7461. Min Act: -0.1700
Data Index: 4458443 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7461. Min Range: -6.7461
Max Act: 6.7149. Min Act: -0.1700
Data Index: 6630711 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7461. Min Range: -6.7461
Max Act: 6.6836. Min Act: -0.1700
Data Index: 648855 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7461. Min Range: -6.7461
Max Act: 6.6524. Min Act: -0.1700
Data Index: 6450090 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7461. Min Range: -6.7461
Max Act: 6.6524. Min Act: -0.1700
Data Index: 2938961 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7461. Min Range: -6.7461
Max Act: 6.6524. Min Act: -0.1700
Data Index: 5301834 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7461. Min Range: -6.7461
Max Act: 6.5899. Min Act: -0.1700
Data Index: 1079442 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7461. Min Range: -6.7461
Max Act: 6.4961. Min Act: -0.1700
Data Index: 7271229 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7461. Min Range: -6.7461
Max Act: 6.4961. Min Act: -0.1700
Data Index: 2487700 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7461. Min Range: -6.7461
Max Act: 6.4961. Min Act: -0.1700
Data Index: 4272762 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7461. Min Range: -6.7461
Max Act: 6.4336. Min Act: -0.1700
Data Index: 6915827 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7461. Min Range: -6.7461
Max Act: 6.4024. Min Act: -0.1700
Data Index: 1069930 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7461. Min Range: -6.7461
Max Act: 6.4024. Min Act: -0.1700
Data Index: 5549784 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7461. Min Range: -6.7461
Max Act: 6.3711. Min Act: -0.1700
Data Index: 3599223 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7461. Min Range: -6.7461
Max Act: 6.3399. Min Act: -0.1700
Data Index: 3740657 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7461. Min Range: -6.7461
Max Act: 6.3399. Min Act: -0.1700
Data Index: 8213214 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7461. Min Range: -6.7461
Max Act: 6.3399. Min Act: -0.1700
Data Index: 1527951 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7461. Min Range: -6.7461
Max Act: 6.3399. Min Act: -0.1700
Data Index: 1823143 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7461. Min Range: -6.7461
Max Act: 6.3086. Min Act: -0.1700
Data Index: 1974640 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #19