Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1286 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.8193. Min Range: -7.8193
Max Act: 7.8193. Min Act: -0.1700
Data Index: 1970607 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8193. Min Range: -7.8193
Max Act: 7.7256. Min Act: -0.1700
Data Index: 2946695 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8193. Min Range: -7.8193
Max Act: 7.6943. Min Act: -0.1700
Data Index: 7022147 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8193. Min Range: -7.8193
Max Act: 7.6631. Min Act: -0.1700
Data Index: 1818071 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8193. Min Range: -7.8193
Max Act: 7.6006. Min Act: -0.1700
Data Index: 7902966 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8193. Min Range: -7.8193
Max Act: 7.5693. Min Act: -0.1700
Data Index: 2548175 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8193. Min Range: -7.8193
Max Act: 7.5381. Min Act: -0.1699
Data Index: 5933325 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8193. Min Range: -7.8193
Max Act: 7.5381. Min Act: -0.1700
Data Index: 8716386 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8193. Min Range: -7.8193
Max Act: 7.5381. Min Act: -0.1700
Data Index: 4486869 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8193. Min Range: -7.8193
Max Act: 7.5068. Min Act: -0.1700
Data Index: 7557168 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8193. Min Range: -7.8193
Max Act: 7.4756. Min Act: -0.1700
Data Index: 3995760 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8193. Min Range: -7.8193
Max Act: 7.4131. Min Act: -0.1700
Data Index: 3602206 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8193. Min Range: -7.8193
Max Act: 7.4443. Min Act: -0.1700
Data Index: 3888581 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8193. Min Range: -7.8193
Max Act: 7.4443. Min Act: -0.1700
Data Index: 7746481 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8193. Min Range: -7.8193
Max Act: 7.4443. Min Act: -0.1700
Data Index: 11292 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8193. Min Range: -7.8193
Max Act: 7.3818. Min Act: -0.1700
Data Index: 3485620 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8193. Min Range: -7.8193
Max Act: 7.3818. Min Act: -0.1700
Data Index: 8613729 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8193. Min Range: -7.8193
Max Act: 7.3818. Min Act: -0.1700
Data Index: 8139155 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8193. Min Range: -7.8193
Max Act: 7.3506. Min Act: -0.1700
Data Index: 6793375 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8193. Min Range: -7.8193
Max Act: 7.3506. Min Act: -0.1700
Data Index: 3288192 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #19