Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4213 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9500. Min Range: -3.9500
Max Act: 3.9500. Min Act: -0.1700
Data Index: 1879026 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9500. Min Range: -3.9500
Max Act: 3.7623. Min Act: -0.1700
Data Index: 6850980 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9500. Min Range: -3.9500
Max Act: 3.7623. Min Act: -0.1700
Data Index: 6469937 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9500. Min Range: -3.9500
Max Act: 3.7311. Min Act: -0.1700
Data Index: 691651 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9500. Min Range: -3.9500
Max Act: 3.7311. Min Act: -0.1700
Data Index: 691650 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9500. Min Range: -3.9500
Max Act: 3.7311. Min Act: -0.1700
Data Index: 898378 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9500. Min Range: -3.9500
Max Act: 3.6998. Min Act: -0.1700
Data Index: 1361618 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9500. Min Range: -3.9500
Max Act: 3.6685. Min Act: -0.1700
Data Index: 4068757 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9500. Min Range: -3.9500
Max Act: 3.6998. Min Act: -0.1700
Data Index: 7413411 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9500. Min Range: -3.9500
Max Act: 3.6372. Min Act: -0.1700
Data Index: 8470123 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9500. Min Range: -3.9500
Max Act: 3.6372. Min Act: -0.1700
Data Index: 7836694 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9500. Min Range: -3.9500
Max Act: 3.6372. Min Act: -0.1700
Data Index: 3493025 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9500. Min Range: -3.9500
Max Act: 3.6372. Min Act: -0.1700
Data Index: 6622207 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9500. Min Range: -3.9500
Max Act: 3.6059. Min Act: -0.1700
Data Index: 1743032 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9500. Min Range: -3.9500
Max Act: 3.6059. Min Act: -0.1700
Data Index: 5098478 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9500. Min Range: -3.9500
Max Act: 3.6059. Min Act: -0.1700
Data Index: 8761146 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9500. Min Range: -3.9500
Max Act: 3.6059. Min Act: -0.1700
Data Index: 7865700 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9500. Min Range: -3.9500
Max Act: 3.6059. Min Act: -0.1700
Data Index: 6759804 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9500. Min Range: -3.9500
Max Act: 3.5433. Min Act: -0.1700
Data Index: 4122811 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9500. Min Range: -3.9500
Max Act: 3.5433. Min Act: -0.1700
Data Index: 8233233 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #19