Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1398 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3817. Min Range: -4.3817
Max Act: 4.3505. Min Act: -0.1700
Data Index: 6753024 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3817. Min Range: -4.3817
Max Act: 4.2567. Min Act: -0.1700
Data Index: 5231624 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3817. Min Range: -4.3817
Max Act: 4.3192. Min Act: -0.1700
Data Index: 2825227 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3817. Min Range: -4.3817
Max Act: 4.3505. Min Act: -0.1700
Data Index: 1993980 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3817. Min Range: -4.3817
Max Act: 4.3817. Min Act: -0.1700
Data Index: 7564159 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3817. Min Range: -4.3817
Max Act: 4.3192. Min Act: -0.1700
Data Index: 723014 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3817. Min Range: -4.3817
Max Act: 4.3192. Min Act: -0.1700
Data Index: 134313 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3817. Min Range: -4.3817
Max Act: 4.3505. Min Act: -0.1700
Data Index: 6301867 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3817. Min Range: -4.3817
Max Act: 4.3192. Min Act: -0.1700
Data Index: 4417870 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3817. Min Range: -4.3817
Max Act: 4.2879. Min Act: -0.1700
Data Index: 650549 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3817. Min Range: -4.3817
Max Act: 4.3192. Min Act: -0.1700
Data Index: 5601105 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3817. Min Range: -4.3817
Max Act: 4.3192. Min Act: -0.1700
Data Index: 6344122 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3817. Min Range: -4.3817
Max Act: 4.3192. Min Act: -0.1700
Data Index: 8820051 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3817. Min Range: -4.3817
Max Act: 4.2567. Min Act: -0.1700
Data Index: 3229 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3817. Min Range: -4.3817
Max Act: 4.3192. Min Act: -0.1700
Data Index: 7010255 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3817. Min Range: -4.3817
Max Act: 4.2879. Min Act: -0.1700
Data Index: 3433297 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3817. Min Range: -4.3817
Max Act: 4.2879. Min Act: -0.1700
Data Index: 83495 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3817. Min Range: -4.3817
Max Act: 4.2879. Min Act: -0.1700
Data Index: 1565228 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3817. Min Range: -4.3817
Max Act: 4.2567. Min Act: -0.1700
Data Index: 1264887 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3817. Min Range: -4.3817
Max Act: 4.2879. Min Act: -0.1700
Data Index: 4500658 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #19