Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3386 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2429. Min Range: -5.2429
Max Act: 5.2429. Min Act: -0.1700
Data Index: 7713874 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2429. Min Range: -5.2429
Max Act: 4.9616. Min Act: -0.1700
Data Index: 6949305 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2429. Min Range: -5.2429
Max Act: 4.9304. Min Act: -0.1700
Data Index: 3846920 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2429. Min Range: -5.2429
Max Act: 4.8991. Min Act: -0.1700
Data Index: 7154030 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2429. Min Range: -5.2429
Max Act: 4.8366. Min Act: -0.1700
Data Index: 742061 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2429. Min Range: -5.2429
Max Act: 4.8366. Min Act: -0.1700
Data Index: 779889 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2429. Min Range: -5.2429
Max Act: 4.8366. Min Act: -0.1700
Data Index: 8661724 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2429. Min Range: -5.2429
Max Act: 4.8366. Min Act: -0.1700
Data Index: 8703963 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2429. Min Range: -5.2429
Max Act: 4.7429. Min Act: -0.1700
Data Index: 8118578 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2429. Min Range: -5.2429
Max Act: 4.7429. Min Act: -0.1700
Data Index: 317244 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2429. Min Range: -5.2429
Max Act: 4.7116. Min Act: -0.1700
Data Index: 3054857 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2429. Min Range: -5.2429
Max Act: 4.7116. Min Act: -0.1700
Data Index: 4249229 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2429. Min Range: -5.2429
Max Act: 4.6804. Min Act: -0.1700
Data Index: 5337169 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2429. Min Range: -5.2429
Max Act: 4.6491. Min Act: -0.1700
Data Index: 3706562 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2429. Min Range: -5.2429
Max Act: 4.6491. Min Act: -0.1700
Data Index: 71488 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2429. Min Range: -5.2429
Max Act: 4.6491. Min Act: -0.1700
Data Index: 1120016 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2429. Min Range: -5.2429
Max Act: 4.6491. Min Act: -0.1700
Data Index: 2007513 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2429. Min Range: -5.2429
Max Act: 4.6491. Min Act: -0.1700
Data Index: 2456192 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2429. Min Range: -5.2429
Max Act: 4.6491. Min Act: -0.1700
Data Index: 5915718 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2429. Min Range: -5.2429
Max Act: 4.6179. Min Act: -0.1700
Data Index: 4654144 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #19