Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 52 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.6699. Min Range: -2.6699
Max Act: 2.6699. Min Act: -0.1700
Data Index: 4662740 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6699. Min Range: -2.6699
Max Act: 2.6699. Min Act: -0.1700
Data Index: 389659 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6699. Min Range: -2.6699
Max Act: 2.6056. Min Act: -0.1699
Data Index: 3043053 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6699. Min Range: -2.6699
Max Act: 2.6056. Min Act: -0.1700
Data Index: 7301442 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6699. Min Range: -2.6699
Max Act: 2.4439. Min Act: -0.1700
Data Index: 2075659 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6699. Min Range: -2.6699
Max Act: 2.4439. Min Act: -0.1688
Data Index: 6130812 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6699. Min Range: -2.6699
Max Act: 2.4439. Min Act: -0.1698
Data Index: 4130624 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6699. Min Range: -2.6699
Max Act: 2.4439. Min Act: -0.1700
Data Index: 5679730 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6699. Min Range: -2.6699
Max Act: 2.4439. Min Act: -0.1699
Data Index: 5601263 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6699. Min Range: -2.6699
Max Act: 2.4439. Min Act: -0.1700
Data Index: 1996637 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6699. Min Range: -2.6699
Max Act: 2.4439. Min Act: -0.1700
Data Index: 4744185 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6699. Min Range: -2.6699
Max Act: 2.4439. Min Act: -0.1700
Data Index: 7312837 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6699. Min Range: -2.6699
Max Act: 2.3787. Min Act: -0.1700
Data Index: 3625132 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6699. Min Range: -2.6699
Max Act: 2.3787. Min Act: -0.1700
Data Index: 3625135 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6699. Min Range: -2.6699
Max Act: 2.3295. Min Act: -0.1700
Data Index: 3957999 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6699. Min Range: -2.6699
Max Act: 2.3295. Min Act: -0.1700
Data Index: 4596435 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6699. Min Range: -2.6699
Max Act: 2.3295. Min Act: -0.1700
Data Index: 3578039 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6699. Min Range: -2.6699
Max Act: 2.3295. Min Act: -0.1700
Data Index: 5124545 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6699. Min Range: -2.6699
Max Act: 2.3131. Min Act: -0.1691
Data Index: 7055248 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6699. Min Range: -2.6699
Max Act: 2.3131. Min Act: -0.1699
Data Index: 173765 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19