Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3381 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0873. Min Range: -6.0873
Max Act: 6.0873. Min Act: -0.1700
Data Index: 3018949 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0873. Min Range: -6.0873
Max Act: 5.7123. Min Act: -0.1700
Data Index: 7552668 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0873. Min Range: -6.0873
Max Act: 5.6498. Min Act: -0.1700
Data Index: 8751297 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0873. Min Range: -6.0873
Max Act: 5.5873. Min Act: -0.1700
Data Index: 6327821 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0873. Min Range: -6.0873
Max Act: 5.6185. Min Act: -0.1700
Data Index: 1608897 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0873. Min Range: -6.0873
Max Act: 5.5873. Min Act: -0.1700
Data Index: 4922935 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0873. Min Range: -6.0873
Max Act: 5.5873. Min Act: -0.1700
Data Index: 917413 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0873. Min Range: -6.0873
Max Act: 5.5873. Min Act: -0.1700
Data Index: 8439172 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0873. Min Range: -6.0873
Max Act: 5.5248. Min Act: -0.1700
Data Index: 5622738 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0873. Min Range: -6.0873
Max Act: 5.5560. Min Act: -0.1700
Data Index: 6328252 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0873. Min Range: -6.0873
Max Act: 5.5560. Min Act: -0.1700
Data Index: 1016630 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0873. Min Range: -6.0873
Max Act: 5.5248. Min Act: -0.1700
Data Index: 3818103 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0873. Min Range: -6.0873
Max Act: 5.5248. Min Act: -0.1700
Data Index: 400117 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0873. Min Range: -6.0873
Max Act: 5.5248. Min Act: -0.1700
Data Index: 2131801 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0873. Min Range: -6.0873
Max Act: 5.5248. Min Act: -0.1700
Data Index: 257734 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0873. Min Range: -6.0873
Max Act: 5.4935. Min Act: -0.1700
Data Index: 773820 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0873. Min Range: -6.0873
Max Act: 5.4935. Min Act: -0.1700
Data Index: 2028593 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0873. Min Range: -6.0873
Max Act: 5.4935. Min Act: -0.1700
Data Index: 7551241 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0873. Min Range: -6.0873
Max Act: 5.4310. Min Act: -0.1700
Data Index: 30064 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0873. Min Range: -6.0873
Max Act: 5.4623. Min Act: -0.1700
Data Index: 3740305 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #19