Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3631 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.3607. Min Range: -2.3607
Max Act: 2.3607. Min Act: -0.1700
Data Index: 8117183 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3607. Min Range: -2.3607
Max Act: 2.2950. Min Act: -0.1700
Data Index: 2327939 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3607. Min Range: -2.3607
Max Act: 2.2950. Min Act: -0.1700
Data Index: 8704141 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3607. Min Range: -2.3607
Max Act: 2.2620. Min Act: -0.1700
Data Index: 553962 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3607. Min Range: -2.3607
Max Act: 2.2620. Min Act: -0.1700
Data Index: 7830190 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3607. Min Range: -2.3607
Max Act: 2.2124. Min Act: -0.1700
Data Index: 3508426 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3607. Min Range: -2.3607
Max Act: 2.2455. Min Act: -0.1700
Data Index: 553990 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3607. Min Range: -2.3607
Max Act: 2.2785. Min Act: -0.1700
Data Index: 854184 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3607. Min Range: -2.3607
Max Act: 2.2124. Min Act: -0.1700
Data Index: 710209 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3607. Min Range: -2.3607
Max Act: 2.2124. Min Act: -0.1700
Data Index: 8676383 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3607. Min Range: -2.3607
Max Act: 2.1958. Min Act: -0.1700
Data Index: 4147215 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3607. Min Range: -2.3607
Max Act: 2.2455. Min Act: -0.1700
Data Index: 1970150 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3607. Min Range: -2.3607
Max Act: 2.2124. Min Act: -0.1700
Data Index: 8317474 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3607. Min Range: -2.3607
Max Act: 2.1958. Min Act: -0.1700
Data Index: 6581629 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3607. Min Range: -2.3607
Max Act: 2.1792. Min Act: -0.1700
Data Index: 4209115 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3607. Min Range: -2.3607
Max Act: 2.2124. Min Act: -0.1700
Data Index: 6626026 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3607. Min Range: -2.3607
Max Act: 2.2290. Min Act: -0.1700
Data Index: 253117 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3607. Min Range: -2.3607
Max Act: 2.2124. Min Act: -0.1700
Data Index: 7143093 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3607. Min Range: -2.3607
Max Act: 2.1958. Min Act: -0.1700
Data Index: 1237518 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3607. Min Range: -2.3607
Max Act: 2.1958. Min Act: -0.1700
Data Index: 1161165 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #19