Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3954 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4832. Min Range: -4.4832
Max Act: 4.4832. Min Act: -0.1700
Data Index: 7827844 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4832. Min Range: -4.4832
Max Act: 4.4832. Min Act: -0.1700
Data Index: 7954670 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4832. Min Range: -4.4832
Max Act: 4.4207. Min Act: -0.1700
Data Index: 3404265 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4832. Min Range: -4.4832
Max Act: 4.4519. Min Act: -0.1700
Data Index: 4377665 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4832. Min Range: -4.4832
Max Act: 4.4207. Min Act: -0.1700
Data Index: 7607274 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4832. Min Range: -4.4832
Max Act: 4.3582. Min Act: -0.1700
Data Index: 8672368 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4832. Min Range: -4.4832
Max Act: 4.3269. Min Act: -0.1700
Data Index: 2523294 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4832. Min Range: -4.4832
Max Act: 4.3269. Min Act: -0.1700
Data Index: 8763407 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4832. Min Range: -4.4832
Max Act: 4.3269. Min Act: -0.1700
Data Index: 3758418 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4832. Min Range: -4.4832
Max Act: 4.2956. Min Act: -0.1700
Data Index: 4644867 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4832. Min Range: -4.4832
Max Act: 4.2956. Min Act: -0.1700
Data Index: 3448632 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4832. Min Range: -4.4832
Max Act: 4.2644. Min Act: -0.1700
Data Index: 6696427 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4832. Min Range: -4.4832
Max Act: 4.2956. Min Act: -0.1700
Data Index: 6133464 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4832. Min Range: -4.4832
Max Act: 4.2644. Min Act: -0.1700
Data Index: 2448273 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4832. Min Range: -4.4832
Max Act: 4.2331. Min Act: -0.1700
Data Index: 4911851 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4832. Min Range: -4.4832
Max Act: 4.2331. Min Act: -0.1700
Data Index: 5529820 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4832. Min Range: -4.4832
Max Act: 4.2331. Min Act: -0.1700
Data Index: 2908892 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4832. Min Range: -4.4832
Max Act: 4.2331. Min Act: -0.1700
Data Index: 3990417 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4832. Min Range: -4.4832
Max Act: 4.2644. Min Act: -0.1700
Data Index: 2443077 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4832. Min Range: -4.4832
Max Act: 4.2331. Min Act: -0.1700
Data Index: 6583340 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #19