Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2178 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.5246. Min Range: -6.5246
Max Act: 6.5246. Min Act: -0.1700
Data Index: 1755968 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5246. Min Range: -6.5246
Max Act: 6.2121. Min Act: -0.1700
Data Index: 2730980 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5246. Min Range: -6.5246
Max Act: 6.1496. Min Act: -0.1700
Data Index: 4111795 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5246. Min Range: -6.5246
Max Act: 6.1184. Min Act: -0.1700
Data Index: 7519111 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5246. Min Range: -6.5246
Max Act: 6.0871. Min Act: -0.1700
Data Index: 3479014 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5246. Min Range: -6.5246
Max Act: 6.0559. Min Act: -0.1700
Data Index: 2618392 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5246. Min Range: -6.5246
Max Act: 6.0871. Min Act: -0.1700
Data Index: 4672948 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5246. Min Range: -6.5246
Max Act: 6.1184. Min Act: -0.1700
Data Index: 79855 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5246. Min Range: -6.5246
Max Act: 6.0871. Min Act: -0.1700
Data Index: 8248500 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5246. Min Range: -6.5246
Max Act: 6.0559. Min Act: -0.1700
Data Index: 221070 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5246. Min Range: -6.5246
Max Act: 6.0559. Min Act: -0.1700
Data Index: 2313810 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5246. Min Range: -6.5246
Max Act: 5.9934. Min Act: -0.1700
Data Index: 7540016 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5246. Min Range: -6.5246
Max Act: 5.9621. Min Act: -0.1700
Data Index: 531 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5246. Min Range: -6.5246
Max Act: 5.9621. Min Act: -0.1700
Data Index: 617285 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5246. Min Range: -6.5246
Max Act: 5.9621. Min Act: -0.1700
Data Index: 1806489 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5246. Min Range: -6.5246
Max Act: 5.9621. Min Act: -0.1700
Data Index: 7572693 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5246. Min Range: -6.5246
Max Act: 5.9621. Min Act: -0.1700
Data Index: 1799086 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5246. Min Range: -6.5246
Max Act: 5.9309. Min Act: -0.1700
Data Index: 528 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5246. Min Range: -6.5246
Max Act: 5.8996. Min Act: -0.1700
Data Index: 3678424 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5246. Min Range: -6.5246
Max Act: 5.9309. Min Act: -0.1700
Data Index: 3678843 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #19