Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4255 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.4086. Min Range: -3.4086
Max Act: 3.4086. Min Act: -0.1700
Data Index: 7795232 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4086. Min Range: -3.4086
Max Act: 3.3773. Min Act: -0.1700
Data Index: 1028612 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4086. Min Range: -3.4086
Max Act: 3.3773. Min Act: -0.1700
Data Index: 6395528 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4086. Min Range: -3.4086
Max Act: 3.2517. Min Act: -0.1700
Data Index: 3577075 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4086. Min Range: -3.4086
Max Act: 3.1731. Min Act: -0.1700
Data Index: 7278038 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4086. Min Range: -3.4086
Max Act: 3.1101. Min Act: -0.1700
Data Index: 2034657 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4086. Min Range: -3.4086
Max Act: 3.0786. Min Act: -0.1700
Data Index: 3018089 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4086. Min Range: -3.4086
Max Act: 3.0786. Min Act: -0.1700
Data Index: 3362811 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4086. Min Range: -3.4086
Max Act: 3.0470. Min Act: -0.1700
Data Index: 4767756 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4086. Min Range: -3.4086
Max Act: 3.0628. Min Act: -0.1700
Data Index: 4812003 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4086. Min Range: -3.4086
Max Act: 3.0628. Min Act: -0.1700
Data Index: 809519 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4086. Min Range: -3.4086
Max Act: 3.0312. Min Act: -0.1700
Data Index: 7278018 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4086. Min Range: -3.4086
Max Act: 3.0154. Min Act: -0.1700
Data Index: 4350516 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4086. Min Range: -3.4086
Max Act: 3.0312. Min Act: -0.1700
Data Index: 7278030 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4086. Min Range: -3.4086
Max Act: 3.0470. Min Act: -0.1700
Data Index: 2942397 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4086. Min Range: -3.4086
Max Act: 3.0312. Min Act: -0.1700
Data Index: 8570342 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4086. Min Range: -3.4086
Max Act: 3.0312. Min Act: -0.1700
Data Index: 6125040 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4086. Min Range: -3.4086
Max Act: 3.0312. Min Act: -0.1700
Data Index: 4596086 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4086. Min Range: -3.4086
Max Act: 3.0154. Min Act: -0.1700
Data Index: 4219268 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4086. Min Range: -3.4086
Max Act: 2.9996. Min Act: -0.1700
Data Index: 466340 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #19