Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3606 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5362. Min Range: -4.5362
Max Act: 4.5362. Min Act: -0.1700
Data Index: 978487 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5362. Min Range: -4.5362
Max Act: 4.4737. Min Act: -0.1700
Data Index: 956759 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5362. Min Range: -4.5362
Max Act: 4.4737. Min Act: -0.1700
Data Index: 7551354 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5362. Min Range: -4.5362
Max Act: 4.4425. Min Act: -0.1700
Data Index: 6939739 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5362. Min Range: -4.5362
Max Act: 4.4425. Min Act: -0.1700
Data Index: 3995139 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5362. Min Range: -4.5362
Max Act: 4.4425. Min Act: -0.1700
Data Index: 7888705 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5362. Min Range: -4.5362
Max Act: 4.4425. Min Act: -0.1700
Data Index: 6189421 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5362. Min Range: -4.5362
Max Act: 4.4425. Min Act: -0.1700
Data Index: 5419923 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5362. Min Range: -4.5362
Max Act: 4.4112. Min Act: -0.1700
Data Index: 3355775 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5362. Min Range: -4.5362
Max Act: 4.3800. Min Act: -0.1700
Data Index: 4272908 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5362. Min Range: -4.5362
Max Act: 4.3800. Min Act: -0.1700
Data Index: 2449697 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5362. Min Range: -4.5362
Max Act: 4.4112. Min Act: -0.1700
Data Index: 7992318 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5362. Min Range: -4.5362
Max Act: 4.4112. Min Act: -0.1700
Data Index: 5317417 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5362. Min Range: -4.5362
Max Act: 4.4112. Min Act: -0.1700
Data Index: 7889159 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5362. Min Range: -4.5362
Max Act: 4.4112. Min Act: -0.1700
Data Index: 332650 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5362. Min Range: -4.5362
Max Act: 4.4112. Min Act: -0.1700
Data Index: 7432072 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5362. Min Range: -4.5362
Max Act: 4.3800. Min Act: -0.1700
Data Index: 5877542 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5362. Min Range: -4.5362
Max Act: 4.3800. Min Act: -0.1700
Data Index: 4381073 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5362. Min Range: -4.5362
Max Act: 4.3800. Min Act: -0.1700
Data Index: 6824221 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5362. Min Range: -4.5362
Max Act: 4.3800. Min Act: -0.1700
Data Index: 1654170 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #19