Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4978 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8153. Min Range: -5.8153
Max Act: 5.8153. Min Act: -0.1700
Data Index: 4011278 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8153. Min Range: -5.8153
Max Act: 5.8153. Min Act: -0.1700
Data Index: 5155449 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8153. Min Range: -5.8153
Max Act: 5.7528. Min Act: -0.1700
Data Index: 280225 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8153. Min Range: -5.8153
Max Act: 5.5340. Min Act: -0.1700
Data Index: 5916651 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8153. Min Range: -5.8153
Max Act: 5.5028. Min Act: -0.1700
Data Index: 2610226 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8153. Min Range: -5.8153
Max Act: 5.4403. Min Act: -0.1700
Data Index: 7797365 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8153. Min Range: -5.8153
Max Act: 5.4715. Min Act: -0.1700
Data Index: 6313660 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8153. Min Range: -5.8153
Max Act: 5.4715. Min Act: -0.1700
Data Index: 6220547 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8153. Min Range: -5.8153
Max Act: 5.4403. Min Act: -0.1700
Data Index: 3821831 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8153. Min Range: -5.8153
Max Act: 5.4403. Min Act: -0.1700
Data Index: 5091443 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8153. Min Range: -5.8153
Max Act: 5.4090. Min Act: -0.1700
Data Index: 7519957 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8153. Min Range: -5.8153
Max Act: 5.4090. Min Act: -0.1700
Data Index: 1047796 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8153. Min Range: -5.8153
Max Act: 5.4403. Min Act: -0.1700
Data Index: 7738688 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8153. Min Range: -5.8153
Max Act: 5.4090. Min Act: -0.1700
Data Index: 3044518 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8153. Min Range: -5.8153
Max Act: 5.3778. Min Act: -0.1700
Data Index: 1155660 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8153. Min Range: -5.8153
Max Act: 5.3778. Min Act: -0.1700
Data Index: 5648960 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8153. Min Range: -5.8153
Max Act: 5.4090. Min Act: -0.1700
Data Index: 89785 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8153. Min Range: -5.8153
Max Act: 5.3778. Min Act: -0.1700
Data Index: 1606045 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8153. Min Range: -5.8153
Max Act: 5.3778. Min Act: -0.1700
Data Index: 2179169 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8153. Min Range: -5.8153
Max Act: 5.3778. Min Act: -0.1700
Data Index: 4678439 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #19