Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2422 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.0736. Min Range: -3.0736
Max Act: 3.0736. Min Act: -0.1700
Data Index: 501129 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0736. Min Range: -3.0736
Max Act: 3.0421. Min Act: -0.1700
Data Index: 5819271 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0736. Min Range: -3.0736
Max Act: 3.0105. Min Act: -0.1700
Data Index: 778370 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0736. Min Range: -3.0736
Max Act: 2.9789. Min Act: -0.1700
Data Index: 3665879 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0736. Min Range: -3.0736
Max Act: 2.8997. Min Act: -0.1700
Data Index: 5717462 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0736. Min Range: -3.0736
Max Act: 2.8838. Min Act: -0.1700
Data Index: 3639945 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0736. Min Range: -3.0736
Max Act: 2.8521. Min Act: -0.1700
Data Index: 518813 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0736. Min Range: -3.0736
Max Act: 2.8521. Min Act: -0.1700
Data Index: 6741134 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0736. Min Range: -3.0736
Max Act: 2.8521. Min Act: -0.1700
Data Index: 7017767 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0736. Min Range: -3.0736
Max Act: 2.8362. Min Act: -0.1700
Data Index: 8406722 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0736. Min Range: -3.0736
Max Act: 2.8362. Min Act: -0.1700
Data Index: 5704608 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0736. Min Range: -3.0736
Max Act: 2.8203. Min Act: -0.1700
Data Index: 1094023 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0736. Min Range: -3.0736
Max Act: 2.8044. Min Act: -0.1700
Data Index: 3830815 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0736. Min Range: -3.0736
Max Act: 2.8044. Min Act: -0.1700
Data Index: 5567440 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0736. Min Range: -3.0736
Max Act: 2.8044. Min Act: -0.1700
Data Index: 3216833 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0736. Min Range: -3.0736
Max Act: 2.7884. Min Act: -0.1700
Data Index: 2290381 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0736. Min Range: -3.0736
Max Act: 2.7725. Min Act: -0.1700
Data Index: 1410758 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0736. Min Range: -3.0736
Max Act: 2.7725. Min Act: -0.1700
Data Index: 6669999 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0736. Min Range: -3.0736
Max Act: 2.7406. Min Act: -0.1700
Data Index: 4642635 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0736. Min Range: -3.0736
Max Act: 2.7565. Min Act: -0.1700
Data Index: 957438 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #19