Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4147 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.4638. Min Range: -3.4638
Max Act: 3.4638. Min Act: -0.1700
Data Index: 6375654 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4638. Min Range: -3.4638
Max Act: 3.4638. Min Act: -0.1700
Data Index: 2721040 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4638. Min Range: -3.4638
Max Act: 3.4011. Min Act: -0.1700
Data Index: 3742778 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4638. Min Range: -3.4638
Max Act: 3.4011. Min Act: -0.1700
Data Index: 5766173 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4638. Min Range: -3.4638
Max Act: 3.3697. Min Act: -0.1700
Data Index: 6243142 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4638. Min Range: -3.4638
Max Act: 3.3697. Min Act: -0.1700
Data Index: 1398064 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4638. Min Range: -3.4638
Max Act: 3.3383. Min Act: -0.1700
Data Index: 3633414 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4638. Min Range: -3.4638
Max Act: 3.3070. Min Act: -0.1700
Data Index: 1644210 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4638. Min Range: -3.4638
Max Act: 3.3070. Min Act: -0.1700
Data Index: 878550 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4638. Min Range: -3.4638
Max Act: 3.3070. Min Act: -0.1700
Data Index: 2205510 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4638. Min Range: -3.4638
Max Act: 3.3383. Min Act: -0.1700
Data Index: 3323199 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4638. Min Range: -3.4638
Max Act: 3.2913. Min Act: -0.1700
Data Index: 1334483 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4638. Min Range: -3.4638
Max Act: 3.2913. Min Act: -0.1700
Data Index: 1961348 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4638. Min Range: -3.4638
Max Act: 3.2756. Min Act: -0.1700
Data Index: 3930100 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4638. Min Range: -3.4638
Max Act: 3.2756. Min Act: -0.1700
Data Index: 3125755 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4638. Min Range: -3.4638
Max Act: 3.2756. Min Act: -0.1700
Data Index: 555031 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4638. Min Range: -3.4638
Max Act: 3.2756. Min Act: -0.1700
Data Index: 1770438 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4638. Min Range: -3.4638
Max Act: 3.2756. Min Act: -0.1700
Data Index: 2813900 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4638. Min Range: -3.4638
Max Act: 3.2598. Min Act: -0.1700
Data Index: 1440377 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4638. Min Range: -3.4638
Max Act: 3.2598. Min Act: -0.1700
Data Index: 4608098 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #19