Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 480 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5643. Min Range: -4.5643
Max Act: 4.5643. Min Act: -0.1700
Data Index: 3014835 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5643. Min Range: -4.5643
Max Act: 4.5331. Min Act: -0.1700
Data Index: 6875029 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5643. Min Range: -4.5643
Max Act: 4.5018. Min Act: -0.1700
Data Index: 1134428 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5643. Min Range: -4.5643
Max Act: 4.5018. Min Act: -0.1700
Data Index: 6418511 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5643. Min Range: -4.5643
Max Act: 4.5018. Min Act: -0.1700
Data Index: 5400167 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5643. Min Range: -4.5643
Max Act: 4.5018. Min Act: -0.1700
Data Index: 7656046 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5643. Min Range: -4.5643
Max Act: 4.5018. Min Act: -0.1700
Data Index: 3050487 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5643. Min Range: -4.5643
Max Act: 4.4706. Min Act: -0.1700
Data Index: 7395678 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5643. Min Range: -4.5643
Max Act: 4.5018. Min Act: -0.1700
Data Index: 1158866 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5643. Min Range: -4.5643
Max Act: 4.4706. Min Act: -0.1700
Data Index: 3467347 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5643. Min Range: -4.5643
Max Act: 4.4393. Min Act: -0.1700
Data Index: 757323 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5643. Min Range: -4.5643
Max Act: 4.4706. Min Act: -0.1700
Data Index: 3593178 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5643. Min Range: -4.5643
Max Act: 4.4393. Min Act: -0.1700
Data Index: 1868352 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5643. Min Range: -4.5643
Max Act: 4.4706. Min Act: -0.1700
Data Index: 4481856 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5643. Min Range: -4.5643
Max Act: 4.5018. Min Act: -0.1700
Data Index: 4643561 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5643. Min Range: -4.5643
Max Act: 4.4706. Min Act: -0.1700
Data Index: 4679437 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5643. Min Range: -4.5643
Max Act: 4.4706. Min Act: -0.1700
Data Index: 4748347 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5643. Min Range: -4.5643
Max Act: 4.4706. Min Act: -0.1700
Data Index: 5235062 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5643. Min Range: -4.5643
Max Act: 4.4393. Min Act: -0.1700
Data Index: 5335054 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5643. Min Range: -4.5643
Max Act: 4.4706. Min Act: -0.1700
Data Index: 2585852 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #19