Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3810 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2190. Min Range: -7.2190
Max Act: 7.2190. Min Act: -0.1700
Data Index: 6050458 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2190. Min Range: -7.2190
Max Act: 7.1252. Min Act: -0.1700
Data Index: 7011234 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2190. Min Range: -7.2190
Max Act: 7.0940. Min Act: -0.1700
Data Index: 2441895 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2190. Min Range: -7.2190
Max Act: 7.0627. Min Act: -0.1700
Data Index: 1530967 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2190. Min Range: -7.2190
Max Act: 6.9690. Min Act: -0.1700
Data Index: 8580659 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2190. Min Range: -7.2190
Max Act: 6.9377. Min Act: -0.1700
Data Index: 8199577 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2190. Min Range: -7.2190
Max Act: 6.9377. Min Act: -0.1700
Data Index: 6926634 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2190. Min Range: -7.2190
Max Act: 6.8752. Min Act: -0.1700
Data Index: 3181660 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2190. Min Range: -7.2190
Max Act: 6.8752. Min Act: -0.1700
Data Index: 8818071 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2190. Min Range: -7.2190
Max Act: 6.8752. Min Act: -0.1700
Data Index: 396183 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2190. Min Range: -7.2190
Max Act: 6.8127. Min Act: -0.1700
Data Index: 7292340 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2190. Min Range: -7.2190
Max Act: 6.8440. Min Act: -0.1700
Data Index: 4384529 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2190. Min Range: -7.2190
Max Act: 6.8752. Min Act: -0.1700
Data Index: 436419 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2190. Min Range: -7.2190
Max Act: 6.8127. Min Act: -0.1700
Data Index: 7654319 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2190. Min Range: -7.2190
Max Act: 6.8127. Min Act: -0.1700
Data Index: 3194718 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2190. Min Range: -7.2190
Max Act: 6.7815. Min Act: -0.1700
Data Index: 3818831 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2190. Min Range: -7.2190
Max Act: 6.7815. Min Act: -0.1700
Data Index: 8744417 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2190. Min Range: -7.2190
Max Act: 6.7815. Min Act: -0.1700
Data Index: 2067639 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2190. Min Range: -7.2190
Max Act: 6.7815. Min Act: -0.1700
Data Index: 7068163 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2190. Min Range: -7.2190
Max Act: 6.7502. Min Act: -0.1700
Data Index: 3895079 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #19