Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 28 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4071. Min Range: -5.4071
Max Act: 5.4071. Min Act: -0.1700
Data Index: 8304293 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4071. Min Range: -5.4071
Max Act: 5.3446. Min Act: -0.1700
Data Index: 4820333 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4071. Min Range: -5.4071
Max Act: 5.2821. Min Act: -0.1700
Data Index: 681827 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4071. Min Range: -5.4071
Max Act: 5.2821. Min Act: -0.1700
Data Index: 4104809 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4071. Min Range: -5.4071
Max Act: 5.3134. Min Act: -0.1700
Data Index: 5167669 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4071. Min Range: -5.4071
Max Act: 5.2821. Min Act: -0.1700
Data Index: 6858935 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4071. Min Range: -5.4071
Max Act: 5.2821. Min Act: -0.1700
Data Index: 2532192 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4071. Min Range: -5.4071
Max Act: 5.1884. Min Act: -0.1700
Data Index: 8326422 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4071. Min Range: -5.4071
Max Act: 5.2509. Min Act: -0.1700
Data Index: 2673979 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4071. Min Range: -5.4071
Max Act: 5.2196. Min Act: -0.1700
Data Index: 4738446 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4071. Min Range: -5.4071
Max Act: 5.2509. Min Act: -0.1700
Data Index: 1750622 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4071. Min Range: -5.4071
Max Act: 5.1884. Min Act: -0.1700
Data Index: 8163875 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4071. Min Range: -5.4071
Max Act: 5.2196. Min Act: -0.1700
Data Index: 165329 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4071. Min Range: -5.4071
Max Act: 5.1884. Min Act: -0.1700
Data Index: 552537 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4071. Min Range: -5.4071
Max Act: 5.1571. Min Act: -0.1700
Data Index: 5637234 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4071. Min Range: -5.4071
Max Act: 5.1571. Min Act: -0.1700
Data Index: 2700771 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4071. Min Range: -5.4071
Max Act: 5.1884. Min Act: -0.1700
Data Index: 1081283 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4071. Min Range: -5.4071
Max Act: 5.1884. Min Act: -0.1700
Data Index: 2712244 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4071. Min Range: -5.4071
Max Act: 5.2196. Min Act: -0.1700
Data Index: 7392970 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4071. Min Range: -5.4071
Max Act: 5.1571. Min Act: -0.1700
Data Index: 3898540 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #19