Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4211 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6445. Min Range: -4.6445
Max Act: 4.6445. Min Act: -0.1700
Data Index: 7007731 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6445. Min Range: -4.6445
Max Act: 4.6133. Min Act: -0.1700
Data Index: 3721071 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6445. Min Range: -4.6445
Max Act: 4.5820. Min Act: -0.1700
Data Index: 6930436 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6445. Min Range: -4.6445
Max Act: 4.4883. Min Act: -0.1700
Data Index: 2164578 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6445. Min Range: -4.6445
Max Act: 4.3320. Min Act: -0.1700
Data Index: 5561144 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6445. Min Range: -4.6445
Max Act: 4.3320. Min Act: -0.1700
Data Index: 2658203 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6445. Min Range: -4.6445
Max Act: 4.3008. Min Act: -0.1700
Data Index: 7643957 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6445. Min Range: -4.6445
Max Act: 4.2383. Min Act: -0.1700
Data Index: 7573256 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6445. Min Range: -4.6445
Max Act: 4.2070. Min Act: -0.1700
Data Index: 1795409 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6445. Min Range: -4.6445
Max Act: 4.1758. Min Act: -0.1700
Data Index: 1996911 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6445. Min Range: -4.6445
Max Act: 4.1758. Min Act: -0.1700
Data Index: 8600189 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6445. Min Range: -4.6445
Max Act: 4.1132. Min Act: -0.1700
Data Index: 5410129 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6445. Min Range: -4.6445
Max Act: 4.1445. Min Act: -0.1700
Data Index: 4194841 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6445. Min Range: -4.6445
Max Act: 4.1132. Min Act: -0.1700
Data Index: 2158136 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6445. Min Range: -4.6445
Max Act: 4.1132. Min Act: -0.1700
Data Index: 524985 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6445. Min Range: -4.6445
Max Act: 4.1132. Min Act: -0.1700
Data Index: 1380469 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6445. Min Range: -4.6445
Max Act: 4.0820. Min Act: -0.1700
Data Index: 724530 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6445. Min Range: -4.6445
Max Act: 4.0820. Min Act: -0.1700
Data Index: 5890860 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6445. Min Range: -4.6445
Max Act: 4.1132. Min Act: -0.1700
Data Index: 5899653 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6445. Min Range: -4.6445
Max Act: 4.0820. Min Act: -0.1700
Data Index: 7863774 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #19