Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2441 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2107. Min Range: -6.2107
Max Act: 6.2107. Min Act: -0.1700
Data Index: 318631 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2107. Min Range: -6.2107
Max Act: 6.1482. Min Act: -0.1700
Data Index: 729494 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2107. Min Range: -6.2107
Max Act: 6.0232. Min Act: -0.1700
Data Index: 17589 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2107. Min Range: -6.2107
Max Act: 5.8044. Min Act: -0.1700
Data Index: 6836987 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2107. Min Range: -6.2107
Max Act: 5.8044. Min Act: -0.1700
Data Index: 5581833 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2107. Min Range: -6.2107
Max Act: 5.7732. Min Act: -0.1700
Data Index: 4462626 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2107. Min Range: -6.2107
Max Act: 5.7107. Min Act: -0.1700
Data Index: 7660756 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2107. Min Range: -6.2107
Max Act: 5.7107. Min Act: -0.1700
Data Index: 5935699 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2107. Min Range: -6.2107
Max Act: 5.6482. Min Act: -0.1700
Data Index: 2553989 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2107. Min Range: -6.2107
Max Act: 5.6482. Min Act: -0.1700
Data Index: 3209279 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2107. Min Range: -6.2107
Max Act: 5.6482. Min Act: -0.1700
Data Index: 4103708 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2107. Min Range: -6.2107
Max Act: 5.6482. Min Act: -0.1700
Data Index: 3852549 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2107. Min Range: -6.2107
Max Act: 5.6169. Min Act: -0.1700
Data Index: 273821 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2107. Min Range: -6.2107
Max Act: 5.5857. Min Act: -0.1700
Data Index: 5387525 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2107. Min Range: -6.2107
Max Act: 5.6169. Min Act: -0.1700
Data Index: 4847546 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2107. Min Range: -6.2107
Max Act: 5.5857. Min Act: -0.1700
Data Index: 7863627 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2107. Min Range: -6.2107
Max Act: 5.5857. Min Act: -0.1700
Data Index: 1945765 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2107. Min Range: -6.2107
Max Act: 5.5544. Min Act: -0.1700
Data Index: 4343243 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2107. Min Range: -6.2107
Max Act: 5.5544. Min Act: -0.1700
Data Index: 3708649 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2107. Min Range: -6.2107
Max Act: 5.5544. Min Act: -0.1700
Data Index: 8002728 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #19