Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5089 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.8469. Min Range: -2.8469
Max Act: 2.8469. Min Act: -0.1700
Data Index: 5625866 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8469. Min Range: -2.8469
Max Act: 2.7992. Min Act: -0.1700
Data Index: 518253 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8469. Min Range: -2.8469
Max Act: 2.7354. Min Act: -0.1700
Data Index: 4949951 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8469. Min Range: -2.8469
Max Act: 2.6874. Min Act: -0.1700
Data Index: 8379157 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8469. Min Range: -2.8469
Max Act: 2.6714. Min Act: -0.1700
Data Index: 8398395 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8469. Min Range: -2.8469
Max Act: 2.6714. Min Act: -0.1700
Data Index: 3106374 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8469. Min Range: -2.8469
Max Act: 2.6714. Min Act: -0.1700
Data Index: 7909110 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8469. Min Range: -2.8469
Max Act: 2.6874. Min Act: -0.1700
Data Index: 4626425 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8469. Min Range: -2.8469
Max Act: 2.6553. Min Act: -0.1700
Data Index: 1368794 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8469. Min Range: -2.8469
Max Act: 2.6393. Min Act: -0.1700
Data Index: 8352655 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8469. Min Range: -2.8469
Max Act: 2.6553. Min Act: -0.1700
Data Index: 2281556 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8469. Min Range: -2.8469
Max Act: 2.6553. Min Act: -0.1700
Data Index: 4177345 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8469. Min Range: -2.8469
Max Act: 2.6232. Min Act: -0.1700
Data Index: 4210519 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8469. Min Range: -2.8469
Max Act: 2.6232. Min Act: -0.1700
Data Index: 2281554 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8469. Min Range: -2.8469
Max Act: 2.6232. Min Act: -0.1700
Data Index: 1227304 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8469. Min Range: -2.8469
Max Act: 2.6071. Min Act: -0.1700
Data Index: 7466873 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8469. Min Range: -2.8469
Max Act: 2.6232. Min Act: -0.1700
Data Index: 7269959 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8469. Min Range: -2.8469
Max Act: 2.6393. Min Act: -0.1700
Data Index: 2631560 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8469. Min Range: -2.8469
Max Act: 2.6071. Min Act: -0.1700
Data Index: 3427169 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8469. Min Range: -2.8469
Max Act: 2.6071. Min Act: -0.1700
Data Index: 1772497 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19