Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4183 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6509. Min Range: -7.6509
Max Act: 7.6509. Min Act: -0.1700
Data Index: 5129097 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6509. Min Range: -7.6509
Max Act: 7.6509. Min Act: -0.1700
Data Index: 1763322 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6509. Min Range: -7.6509
Max Act: 7.5884. Min Act: -0.1700
Data Index: 4100226 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6509. Min Range: -7.6509
Max Act: 7.5259. Min Act: -0.1700
Data Index: 7282029 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6509. Min Range: -7.6509
Max Act: 7.4634. Min Act: -0.1700
Data Index: 5134033 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6509. Min Range: -7.6509
Max Act: 7.5259. Min Act: -0.1700
Data Index: 4652259 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6509. Min Range: -7.6509
Max Act: 7.5259. Min Act: -0.1700
Data Index: 830063 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6509. Min Range: -7.6509
Max Act: 7.5884. Min Act: -0.1700
Data Index: 271248 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6509. Min Range: -7.6509
Max Act: 7.5259. Min Act: -0.1700
Data Index: 8498368 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6509. Min Range: -7.6509
Max Act: 7.5259. Min Act: -0.1699
Data Index: 8274358 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6509. Min Range: -7.6509
Max Act: 7.5259. Min Act: -0.1700
Data Index: 5974281 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6509. Min Range: -7.6509
Max Act: 7.4634. Min Act: -0.1700
Data Index: 3968186 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6509. Min Range: -7.6509
Max Act: 7.4634. Min Act: -0.1699
Data Index: 3167306 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6509. Min Range: -7.6509
Max Act: 7.4634. Min Act: -0.1700
Data Index: 1623315 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6509. Min Range: -7.6509
Max Act: 7.4634. Min Act: -0.1645
Data Index: 4496601 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6509. Min Range: -7.6509
Max Act: 7.4634. Min Act: -0.1699
Data Index: 4547705 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6509. Min Range: -7.6509
Max Act: 7.4634. Min Act: -0.1700
Data Index: 1801051 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6509. Min Range: -7.6509
Max Act: 7.4634. Min Act: -0.1699
Data Index: 4743252 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6509. Min Range: -7.6509
Max Act: 7.4634. Min Act: -0.1700
Data Index: 4818182 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6509. Min Range: -7.6509
Max Act: 7.4634. Min Act: -0.1700
Data Index: 4845508 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #19