Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4088 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2386. Min Range: -5.2386
Max Act: 5.2386. Min Act: -0.1700
Data Index: 4595448 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2386. Min Range: -5.2386
Max Act: 5.2073. Min Act: -0.1700
Data Index: 2592486 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2386. Min Range: -5.2386
Max Act: 5.2073. Min Act: -0.1700
Data Index: 7616338 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2386. Min Range: -5.2386
Max Act: 5.2073. Min Act: -0.1700
Data Index: 7800746 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2386. Min Range: -5.2386
Max Act: 5.1761. Min Act: -0.1700
Data Index: 4045389 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2386. Min Range: -5.2386
Max Act: 5.1761. Min Act: -0.1700
Data Index: 5171597 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2386. Min Range: -5.2386
Max Act: 5.1761. Min Act: -0.1700
Data Index: 8348871 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2386. Min Range: -5.2386
Max Act: 5.1448. Min Act: -0.1700
Data Index: 5025694 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2386. Min Range: -5.2386
Max Act: 5.1761. Min Act: -0.1700
Data Index: 4555019 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2386. Min Range: -5.2386
Max Act: 5.1761. Min Act: -0.1700
Data Index: 8088719 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2386. Min Range: -5.2386
Max Act: 5.1761. Min Act: -0.1700
Data Index: 8027258 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2386. Min Range: -5.2386
Max Act: 5.1761. Min Act: -0.1700
Data Index: 2060272 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2386. Min Range: -5.2386
Max Act: 5.1448. Min Act: -0.1700
Data Index: 6370226 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2386. Min Range: -5.2386
Max Act: 5.1761. Min Act: -0.1700
Data Index: 1848782 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2386. Min Range: -5.2386
Max Act: 5.1761. Min Act: -0.1699
Data Index: 236857 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2386. Min Range: -5.2386
Max Act: 5.1761. Min Act: -0.1700
Data Index: 1139346 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2386. Min Range: -5.2386
Max Act: 5.1761. Min Act: -0.1700
Data Index: 1848783 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2386. Min Range: -5.2386
Max Act: 5.1761. Min Act: -0.1700
Data Index: 3757015 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2386. Min Range: -5.2386
Max Act: 5.1761. Min Act: -0.1700
Data Index: 7124619 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2386. Min Range: -5.2386
Max Act: 5.1761. Min Act: -0.1700
Data Index: 735433 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19