Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3351 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0392. Min Range: -4.0392
Max Act: 4.0392. Min Act: -0.1700
Data Index: 886997 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0392. Min Range: -4.0392
Max Act: 4.0392. Min Act: -0.1700
Data Index: 7967546 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0392. Min Range: -4.0392
Max Act: 3.9767. Min Act: -0.1700
Data Index: 2288952 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0392. Min Range: -4.0392
Max Act: 3.9767. Min Act: -0.1700
Data Index: 6638531 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0392. Min Range: -4.0392
Max Act: 4.0079. Min Act: -0.1700
Data Index: 993444 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0392. Min Range: -4.0392
Max Act: 3.9141. Min Act: -0.1700
Data Index: 6205984 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0392. Min Range: -4.0392
Max Act: 3.9454. Min Act: -0.1700
Data Index: 4024173 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0392. Min Range: -4.0392
Max Act: 3.9141. Min Act: -0.1700
Data Index: 4091238 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0392. Min Range: -4.0392
Max Act: 3.8829. Min Act: -0.1700
Data Index: 4994220 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0392. Min Range: -4.0392
Max Act: 3.9141. Min Act: -0.1700
Data Index: 5823641 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0392. Min Range: -4.0392
Max Act: 3.9454. Min Act: -0.1700
Data Index: 2988552 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0392. Min Range: -4.0392
Max Act: 3.9141. Min Act: -0.1700
Data Index: 6528384 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0392. Min Range: -4.0392
Max Act: 3.9141. Min Act: -0.1700
Data Index: 2769945 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0392. Min Range: -4.0392
Max Act: 3.9141. Min Act: -0.1700
Data Index: 1676368 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0392. Min Range: -4.0392
Max Act: 3.9141. Min Act: -0.1700
Data Index: 6736537 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0392. Min Range: -4.0392
Max Act: 3.8829. Min Act: -0.1700
Data Index: 5396090 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0392. Min Range: -4.0392
Max Act: 3.8829. Min Act: -0.1700
Data Index: 3887544 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0392. Min Range: -4.0392
Max Act: 3.8829. Min Act: -0.1700
Data Index: 6048552 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0392. Min Range: -4.0392
Max Act: 3.8829. Min Act: -0.1700
Data Index: 2458015 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0392. Min Range: -4.0392
Max Act: 3.8829. Min Act: -0.1700
Data Index: 1799437 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #19