Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3266 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1444. Min Range: -9.1444
Max Act: 9.1444. Min Act: -0.1695
Data Index: 5709680 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1444. Min Range: -9.1444
Max Act: 8.8944. Min Act: -0.1700
Data Index: 1247027 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1444. Min Range: -9.1444
Max Act: 8.8944. Min Act: -0.1700
Data Index: 4579152 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1444. Min Range: -9.1444
Max Act: 8.8944. Min Act: -0.1700
Data Index: 107932 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1444. Min Range: -9.1444
Max Act: 8.8319. Min Act: -0.1700
Data Index: 7299090 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1444. Min Range: -9.1444
Max Act: 8.7694. Min Act: -0.1700
Data Index: 7720592 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1444. Min Range: -9.1444
Max Act: 8.7694. Min Act: -0.1700
Data Index: 4472695 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1444. Min Range: -9.1444
Max Act: 8.7694. Min Act: -0.1700
Data Index: 6625758 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1444. Min Range: -9.1444
Max Act: 8.7069. Min Act: -0.1700
Data Index: 4427236 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1444. Min Range: -9.1444
Max Act: 8.7069. Min Act: -0.1700
Data Index: 1744894 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1444. Min Range: -9.1444
Max Act: 8.7069. Min Act: -0.1700
Data Index: 3653905 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1444. Min Range: -9.1444
Max Act: 8.6444. Min Act: -0.1700
Data Index: 7524515 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1444. Min Range: -9.1444
Max Act: 8.6444. Min Act: -0.1700
Data Index: 43609 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1444. Min Range: -9.1444
Max Act: 8.6444. Min Act: -0.1700
Data Index: 1865480 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1444. Min Range: -9.1444
Max Act: 8.6444. Min Act: -0.1700
Data Index: 519290 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1444. Min Range: -9.1444
Max Act: 8.5819. Min Act: -0.1700
Data Index: 5245115 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1444. Min Range: -9.1444
Max Act: 8.5819. Min Act: -0.1700
Data Index: 7488169 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1444. Min Range: -9.1444
Max Act: 8.5194. Min Act: -0.1700
Data Index: 1871974 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1444. Min Range: -9.1444
Max Act: 8.5194. Min Act: -0.1700
Data Index: 1931881 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1444. Min Range: -9.1444
Max Act: 8.5194. Min Act: -0.1700
Data Index: 3440418 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #19