Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 103 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2327. Min Range: -5.2327
Max Act: 5.2327. Min Act: -0.1700
Data Index: 3775846 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2327. Min Range: -5.2327
Max Act: 5.1390. Min Act: -0.1700
Data Index: 587518 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2327. Min Range: -5.2327
Max Act: 5.1702. Min Act: -0.1700
Data Index: 2133545 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2327. Min Range: -5.2327
Max Act: 5.1077. Min Act: -0.1700
Data Index: 4636012 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2327. Min Range: -5.2327
Max Act: 5.0765. Min Act: -0.1700
Data Index: 6937349 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2327. Min Range: -5.2327
Max Act: 5.0765. Min Act: -0.1700
Data Index: 1302964 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2327. Min Range: -5.2327
Max Act: 5.0765. Min Act: -0.1700
Data Index: 3011581 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2327. Min Range: -5.2327
Max Act: 5.0452. Min Act: -0.1700
Data Index: 216092 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2327. Min Range: -5.2327
Max Act: 5.0765. Min Act: -0.1700
Data Index: 6507069 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2327. Min Range: -5.2327
Max Act: 5.0452. Min Act: -0.1700
Data Index: 4461125 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2327. Min Range: -5.2327
Max Act: 5.0452. Min Act: -0.1700
Data Index: 7512869 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2327. Min Range: -5.2327
Max Act: 5.0765. Min Act: -0.1700
Data Index: 1940549 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2327. Min Range: -5.2327
Max Act: 5.0452. Min Act: -0.1700
Data Index: 7725675 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2327. Min Range: -5.2327
Max Act: 5.0452. Min Act: -0.1700
Data Index: 2447657 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2327. Min Range: -5.2327
Max Act: 4.9827. Min Act: -0.1700
Data Index: 2347587 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2327. Min Range: -5.2327
Max Act: 5.0452. Min Act: -0.1700
Data Index: 8793465 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2327. Min Range: -5.2327
Max Act: 5.0140. Min Act: -0.1700
Data Index: 8297690 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2327. Min Range: -5.2327
Max Act: 5.0140. Min Act: -0.1700
Data Index: 2992281 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2327. Min Range: -5.2327
Max Act: 4.9827. Min Act: -0.1700
Data Index: 6739958 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2327. Min Range: -5.2327
Max Act: 4.9515. Min Act: -0.1700
Data Index: 6225335 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #19