Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3785 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4062. Min Range: -6.4062
Max Act: 6.4062. Min Act: -0.1700
Data Index: 4832194 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4062. Min Range: -6.4062
Max Act: 6.3749. Min Act: -0.1700
Data Index: 8530137 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4062. Min Range: -6.4062
Max Act: 6.3124. Min Act: -0.1700
Data Index: 4515541 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4062. Min Range: -6.4062
Max Act: 6.2812. Min Act: -0.1700
Data Index: 2361065 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4062. Min Range: -6.4062
Max Act: 6.2499. Min Act: -0.1700
Data Index: 4625232 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4062. Min Range: -6.4062
Max Act: 6.2499. Min Act: -0.1700
Data Index: 3396617 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4062. Min Range: -6.4062
Max Act: 6.2187. Min Act: -0.1700
Data Index: 5483351 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4062. Min Range: -6.4062
Max Act: 6.2187. Min Act: -0.1700
Data Index: 2015001 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4062. Min Range: -6.4062
Max Act: 6.2187. Min Act: -0.1700
Data Index: 2619938 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4062. Min Range: -6.4062
Max Act: 6.2187. Min Act: -0.1700
Data Index: 3886645 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4062. Min Range: -6.4062
Max Act: 6.1874. Min Act: -0.1700
Data Index: 381835 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4062. Min Range: -6.4062
Max Act: 6.1562. Min Act: -0.1700
Data Index: 2284495 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4062. Min Range: -6.4062
Max Act: 6.1562. Min Act: -0.1700
Data Index: 5482031 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4062. Min Range: -6.4062
Max Act: 6.1562. Min Act: -0.1700
Data Index: 1102379 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4062. Min Range: -6.4062
Max Act: 6.1562. Min Act: -0.1700
Data Index: 3604594 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4062. Min Range: -6.4062
Max Act: 6.1249. Min Act: -0.1700
Data Index: 3438713 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4062. Min Range: -6.4062
Max Act: 6.1249. Min Act: -0.1700
Data Index: 2102115 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4062. Min Range: -6.4062
Max Act: 6.1249. Min Act: -0.1700
Data Index: 8809808 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4062. Min Range: -6.4062
Max Act: 6.1249. Min Act: -0.1700
Data Index: 5595622 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4062. Min Range: -6.4062
Max Act: 6.0937. Min Act: -0.1700
Data Index: 2072253 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #19