Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 338 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8884. Min Range: -8.8884
Max Act: 8.8884. Min Act: -0.1700
Data Index: 1931026 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8884. Min Range: -8.8884
Max Act: 8.7009. Min Act: -0.1700
Data Index: 4647937 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8884. Min Range: -8.8884
Max Act: 8.5134. Min Act: -0.1700
Data Index: 6123557 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8884. Min Range: -8.8884
Max Act: 8.4509. Min Act: -0.1700
Data Index: 5010196 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8884. Min Range: -8.8884
Max Act: 8.4509. Min Act: -0.1700
Data Index: 6206013 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8884. Min Range: -8.8884
Max Act: 8.3884. Min Act: -0.1700
Data Index: 3147754 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8884. Min Range: -8.8884
Max Act: 8.3884. Min Act: -0.1700
Data Index: 87311 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8884. Min Range: -8.8884
Max Act: 8.3259. Min Act: -0.1700
Data Index: 7462382 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8884. Min Range: -8.8884
Max Act: 8.3259. Min Act: -0.1700
Data Index: 658994 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8884. Min Range: -8.8884
Max Act: 8.2634. Min Act: -0.1700
Data Index: 658993 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8884. Min Range: -8.8884
Max Act: 8.2634. Min Act: -0.1700
Data Index: 1943845 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8884. Min Range: -8.8884
Max Act: 8.2634. Min Act: -0.1700
Data Index: 1957823 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8884. Min Range: -8.8884
Max Act: 8.2634. Min Act: -0.1700
Data Index: 3637498 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8884. Min Range: -8.8884
Max Act: 8.2009. Min Act: -0.1700
Data Index: 8180611 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8884. Min Range: -8.8884
Max Act: 8.2009. Min Act: -0.1700
Data Index: 3330384 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8884. Min Range: -8.8884
Max Act: 8.2009. Min Act: -0.1700
Data Index: 69072 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8884. Min Range: -8.8884
Max Act: 8.2009. Min Act: -0.1700
Data Index: 72788 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8884. Min Range: -8.8884
Max Act: 8.1384. Min Act: -0.1700
Data Index: 1329241 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8884. Min Range: -8.8884
Max Act: 8.1384. Min Act: -0.1700
Data Index: 3838492 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8884. Min Range: -8.8884
Max Act: 8.0759. Min Act: -0.1700
Data Index: 8134167 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #19