Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3630 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1534. Min Range: -6.1534
Max Act: 6.1534. Min Act: -0.1700
Data Index: 4312426 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1534. Min Range: -6.1534
Max Act: 5.4972. Min Act: -0.1700
Data Index: 4819839 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1534. Min Range: -6.1534
Max Act: 5.4347. Min Act: -0.1700
Data Index: 7098094 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1534. Min Range: -6.1534
Max Act: 5.3409. Min Act: -0.1700
Data Index: 6205407 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1534. Min Range: -6.1534
Max Act: 5.3097. Min Act: -0.1700
Data Index: 323221 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1534. Min Range: -6.1534
Max Act: 5.3409. Min Act: -0.1700
Data Index: 8473132 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1534. Min Range: -6.1534
Max Act: 5.2784. Min Act: -0.1700
Data Index: 6920114 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1534. Min Range: -6.1534
Max Act: 5.2472. Min Act: -0.1700
Data Index: 4130341 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1534. Min Range: -6.1534
Max Act: 5.2784. Min Act: -0.1700
Data Index: 2616096 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1534. Min Range: -6.1534
Max Act: 5.2784. Min Act: -0.1700
Data Index: 355491 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1534. Min Range: -6.1534
Max Act: 5.2784. Min Act: -0.1700
Data Index: 2681441 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1534. Min Range: -6.1534
Max Act: 5.2159. Min Act: -0.1700
Data Index: 1614462 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1534. Min Range: -6.1534
Max Act: 5.2472. Min Act: -0.1700
Data Index: 955470 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1534. Min Range: -6.1534
Max Act: 5.2472. Min Act: -0.1700
Data Index: 2178430 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1534. Min Range: -6.1534
Max Act: 5.2784. Min Act: -0.1700
Data Index: 923351 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1534. Min Range: -6.1534
Max Act: 5.2472. Min Act: -0.1700
Data Index: 5465976 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1534. Min Range: -6.1534
Max Act: 5.2159. Min Act: -0.1700
Data Index: 3653864 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1534. Min Range: -6.1534
Max Act: 5.2159. Min Act: -0.1700
Data Index: 5185423 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1534. Min Range: -6.1534
Max Act: 5.1847. Min Act: -0.1700
Data Index: 4040610 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1534. Min Range: -6.1534
Max Act: 5.2472. Min Act: -0.1700
Data Index: 8400878 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #19