Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4059 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.6755. Min Range: -2.6755
Max Act: 2.6755. Min Act: -0.1700
Data Index: 5630242 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6755. Min Range: -2.6755
Max Act: 2.6755. Min Act: -0.1700
Data Index: 3757079 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6755. Min Range: -2.6755
Max Act: 2.6595. Min Act: -0.1700
Data Index: 6124341 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6755. Min Range: -2.6755
Max Act: 2.6274. Min Act: -0.1700
Data Index: 3997221 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6755. Min Range: -2.6755
Max Act: 2.6113. Min Act: -0.1700
Data Index: 2369069 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6755. Min Range: -2.6755
Max Act: 2.5952. Min Act: -0.1700
Data Index: 8373423 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6755. Min Range: -2.6755
Max Act: 2.5307. Min Act: -0.1700
Data Index: 5775863 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6755. Min Range: -2.6755
Max Act: 2.5307. Min Act: -0.1700
Data Index: 3607819 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6755. Min Range: -2.6755
Max Act: 2.5468. Min Act: -0.1700
Data Index: 8579962 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6755. Min Range: -2.6755
Max Act: 2.5307. Min Act: -0.1700
Data Index: 3138672 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6755. Min Range: -2.6755
Max Act: 2.5468. Min Act: -0.1700
Data Index: 2879194 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6755. Min Range: -2.6755
Max Act: 2.5307. Min Act: -0.1700
Data Index: 5024385 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6755. Min Range: -2.6755
Max Act: 2.5307. Min Act: -0.1700
Data Index: 4643401 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6755. Min Range: -2.6755
Max Act: 2.5307. Min Act: -0.1700
Data Index: 7342077 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6755. Min Range: -2.6755
Max Act: 2.5145. Min Act: -0.1700
Data Index: 7932858 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6755. Min Range: -2.6755
Max Act: 2.5145. Min Act: -0.1700
Data Index: 8083171 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6755. Min Range: -2.6755
Max Act: 2.5145. Min Act: -0.1700
Data Index: 5914488 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6755. Min Range: -2.6755
Max Act: 2.5145. Min Act: -0.1700
Data Index: 5638864 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6755. Min Range: -2.6755
Max Act: 2.5145. Min Act: -0.1700
Data Index: 459503 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6755. Min Range: -2.6755
Max Act: 2.5307. Min Act: -0.1700
Data Index: 7636024 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #19