Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3682 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7232. Min Range: -5.7232
Max Act: 5.7232. Min Act: -0.1700
Data Index: 3110713 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7232. Min Range: -5.7232
Max Act: 5.6920. Min Act: -0.1700
Data Index: 7524745 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7232. Min Range: -5.7232
Max Act: 5.6920. Min Act: -0.1700
Data Index: 4795743 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7232. Min Range: -5.7232
Max Act: 5.6295. Min Act: -0.1700
Data Index: 147640 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7232. Min Range: -5.7232
Max Act: 5.6295. Min Act: -0.1700
Data Index: 7515166 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7232. Min Range: -5.7232
Max Act: 5.6295. Min Act: -0.1700
Data Index: 715601 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7232. Min Range: -5.7232
Max Act: 5.6295. Min Act: -0.1700
Data Index: 4405563 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7232. Min Range: -5.7232
Max Act: 5.6295. Min Act: -0.1700
Data Index: 2866943 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7232. Min Range: -5.7232
Max Act: 5.5670. Min Act: -0.1700
Data Index: 7672551 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7232. Min Range: -5.7232
Max Act: 5.5982. Min Act: -0.1700
Data Index: 5085665 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7232. Min Range: -5.7232
Max Act: 5.5982. Min Act: -0.1700
Data Index: 5805473 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7232. Min Range: -5.7232
Max Act: 5.5670. Min Act: -0.1700
Data Index: 653228 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7232. Min Range: -5.7232
Max Act: 5.5670. Min Act: -0.1700
Data Index: 5827889 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7232. Min Range: -5.7232
Max Act: 5.5670. Min Act: -0.1700
Data Index: 7391275 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7232. Min Range: -5.7232
Max Act: 5.5670. Min Act: -0.1700
Data Index: 6731954 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7232. Min Range: -5.7232
Max Act: 5.5670. Min Act: -0.1700
Data Index: 7898339 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7232. Min Range: -5.7232
Max Act: 5.5670. Min Act: -0.1700
Data Index: 7898332 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7232. Min Range: -5.7232
Max Act: 5.5357. Min Act: -0.1700
Data Index: 6374673 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7232. Min Range: -5.7232
Max Act: 5.5357. Min Act: -0.1700
Data Index: 717413 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7232. Min Range: -5.7232
Max Act: 5.5357. Min Act: -0.1700
Data Index: 1417723 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #19