Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5085 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.7978. Min Range: -2.7978
Max Act: 2.7978. Min Act: -0.1700
Data Index: 6525637 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7978. Min Range: -2.7978
Max Act: 2.7020. Min Act: -0.1700
Data Index: 610944 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7978. Min Range: -2.7978
Max Act: 2.5897. Min Act: -0.1700
Data Index: 1810165 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7978. Min Range: -2.7978
Max Act: 2.6058. Min Act: -0.1700
Data Index: 8151687 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7978. Min Range: -2.7978
Max Act: 2.6058. Min Act: -0.1700
Data Index: 8164720 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7978. Min Range: -2.7978
Max Act: 2.5897. Min Act: -0.1700
Data Index: 7836347 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7978. Min Range: -2.7978
Max Act: 2.5897. Min Act: -0.1700
Data Index: 610933 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7978. Min Range: -2.7978
Max Act: 2.5897. Min Act: -0.1700
Data Index: 1515460 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7978. Min Range: -2.7978
Max Act: 2.5897. Min Act: -0.1700
Data Index: 610942 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7978. Min Range: -2.7978
Max Act: 2.5897. Min Act: -0.1700
Data Index: 8151691 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7978. Min Range: -2.7978
Max Act: 2.5736. Min Act: -0.1700
Data Index: 8151694 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7978. Min Range: -2.7978
Max Act: 2.5736. Min Act: -0.1700
Data Index: 610940 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7978. Min Range: -2.7978
Max Act: 2.5251. Min Act: -0.1700
Data Index: 6099956 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7978. Min Range: -2.7978
Max Act: 2.5574. Min Act: -0.1700
Data Index: 3364254 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7978. Min Range: -2.7978
Max Act: 2.5413. Min Act: -0.1700
Data Index: 610934 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7978. Min Range: -2.7978
Max Act: 2.5574. Min Act: -0.1700
Data Index: 610936 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7978. Min Range: -2.7978
Max Act: 2.5251. Min Act: -0.1700
Data Index: 4239943 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7978. Min Range: -2.7978
Max Act: 2.5413. Min Act: -0.1700
Data Index: 8148961 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7978. Min Range: -2.7978
Max Act: 2.5413. Min Act: -0.1700
Data Index: 162079 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7978. Min Range: -2.7978
Max Act: 2.5251. Min Act: -0.1700
Data Index: 5254659 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #19