Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 322 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.3726. Min Range: -2.3726
Max Act: 2.3726. Min Act: -0.1700
Data Index: 5227602 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3726. Min Range: -2.3726
Max Act: 2.3398. Min Act: -0.1700
Data Index: 372010 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3726. Min Range: -2.3726
Max Act: 2.3070. Min Act: -0.1700
Data Index: 3532904 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3726. Min Range: -2.3726
Max Act: 2.3398. Min Act: -0.1700
Data Index: 2027471 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3726. Min Range: -2.3726
Max Act: 2.3234. Min Act: -0.1700
Data Index: 6153477 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3726. Min Range: -2.3726
Max Act: 2.3070. Min Act: -0.1700
Data Index: 258806 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3726. Min Range: -2.3726
Max Act: 2.3070. Min Act: -0.1700
Data Index: 7634716 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3726. Min Range: -2.3726
Max Act: 2.2905. Min Act: -0.1700
Data Index: 870842 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3726. Min Range: -2.3726
Max Act: 2.2905. Min Act: -0.1700
Data Index: 4135171 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3726. Min Range: -2.3726
Max Act: 2.2740. Min Act: -0.1700
Data Index: 1348699 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3726. Min Range: -2.3726
Max Act: 2.2740. Min Act: -0.1700
Data Index: 5132076 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3726. Min Range: -2.3726
Max Act: 2.2740. Min Act: -0.1700
Data Index: 6711226 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3726. Min Range: -2.3726
Max Act: 2.2740. Min Act: -0.1700
Data Index: 4932186 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3726. Min Range: -2.3726
Max Act: 2.2740. Min Act: -0.1700
Data Index: 5999351 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3726. Min Range: -2.3726
Max Act: 2.2740. Min Act: -0.1700
Data Index: 1869126 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3726. Min Range: -2.3726
Max Act: 2.2575. Min Act: -0.1700
Data Index: 1946310 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3726. Min Range: -2.3726
Max Act: 2.2575. Min Act: -0.1700
Data Index: 1716246 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3726. Min Range: -2.3726
Max Act: 2.2575. Min Act: -0.1700
Data Index: 1674945 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3726. Min Range: -2.3726
Max Act: 2.2575. Min Act: -0.1700
Data Index: 6199460 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3726. Min Range: -2.3726
Max Act: 2.2575. Min Act: -0.1700
Data Index: 3403402 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #19