Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4054 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7002. Min Range: -4.7002
Max Act: 4.7002. Min Act: -0.1700
Data Index: 19026 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7002. Min Range: -4.7002
Max Act: 4.6689. Min Act: -0.1700
Data Index: 8201376 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7002. Min Range: -4.7002
Max Act: 4.7002. Min Act: -0.1700
Data Index: 1406861 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7002. Min Range: -4.7002
Max Act: 4.6689. Min Act: -0.1700
Data Index: 4112624 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7002. Min Range: -4.7002
Max Act: 4.5752. Min Act: -0.1700
Data Index: 117377 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7002. Min Range: -4.7002
Max Act: 4.6064. Min Act: -0.1700
Data Index: 5890188 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7002. Min Range: -4.7002
Max Act: 4.5752. Min Act: -0.1700
Data Index: 7720071 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7002. Min Range: -4.7002
Max Act: 4.5752. Min Act: -0.1700
Data Index: 1802675 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7002. Min Range: -4.7002
Max Act: 4.5752. Min Act: -0.1700
Data Index: 6075862 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7002. Min Range: -4.7002
Max Act: 4.5752. Min Act: -0.1700
Data Index: 8824846 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7002. Min Range: -4.7002
Max Act: 4.5439. Min Act: -0.1700
Data Index: 2168501 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7002. Min Range: -4.7002
Max Act: 4.5752. Min Act: -0.1700
Data Index: 2999808 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7002. Min Range: -4.7002
Max Act: 4.5752. Min Act: -0.1700
Data Index: 8598124 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7002. Min Range: -4.7002
Max Act: 4.5439. Min Act: -0.1700
Data Index: 371636 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7002. Min Range: -4.7002
Max Act: 4.5752. Min Act: -0.1700
Data Index: 7714564 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7002. Min Range: -4.7002
Max Act: 4.5127. Min Act: -0.1700
Data Index: 2304002 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7002. Min Range: -4.7002
Max Act: 4.5439. Min Act: -0.1696
Data Index: 1572414 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7002. Min Range: -4.7002
Max Act: 4.5439. Min Act: -0.1699
Data Index: 2466703 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7002. Min Range: -4.7002
Max Act: 4.5127. Min Act: -0.1700
Data Index: 3774525 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7002. Min Range: -4.7002
Max Act: 4.5127. Min Act: -0.1700
Data Index: 2614389 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #19