Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 22 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6039. Min Range: -3.6039
Max Act: 3.5726. Min Act: -0.1700
Data Index: 3326089 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6039. Min Range: -3.6039
Max Act: 3.6039. Min Act: -0.1700
Data Index: 2954299 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6039. Min Range: -3.6039
Max Act: 3.4160. Min Act: -0.1700
Data Index: 3326090 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6039. Min Range: -3.6039
Max Act: 3.4317. Min Act: -0.1700
Data Index: 4685251 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6039. Min Range: -3.6039
Max Act: 3.4160. Min Act: -0.1700
Data Index: 3468307 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6039. Min Range: -3.6039
Max Act: 3.4003. Min Act: -0.1700
Data Index: 1451342 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6039. Min Range: -3.6039
Max Act: 3.3689. Min Act: -0.1700
Data Index: 3200561 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6039. Min Range: -3.6039
Max Act: 3.3689. Min Act: -0.1700
Data Index: 2411001 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6039. Min Range: -3.6039
Max Act: 3.3689. Min Act: -0.1700
Data Index: 802769 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6039. Min Range: -3.6039
Max Act: 3.3219. Min Act: -0.1700
Data Index: 460414 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6039. Min Range: -3.6039
Max Act: 3.3689. Min Act: -0.1700
Data Index: 5912964 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6039. Min Range: -3.6039
Max Act: 3.3533. Min Act: -0.1700
Data Index: 1376989 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6039. Min Range: -3.6039
Max Act: 3.3376. Min Act: -0.1700
Data Index: 8830824 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6039. Min Range: -3.6039
Max Act: 3.3376. Min Act: -0.1700
Data Index: 1465926 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6039. Min Range: -3.6039
Max Act: 3.3219. Min Act: -0.1700
Data Index: 3326091 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6039. Min Range: -3.6039
Max Act: 3.3376. Min Act: -0.1700
Data Index: 6283865 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6039. Min Range: -3.6039
Max Act: 3.2905. Min Act: -0.1700
Data Index: 402779 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6039. Min Range: -3.6039
Max Act: 3.2748. Min Act: -0.1700
Data Index: 2678920 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6039. Min Range: -3.6039
Max Act: 3.2591. Min Act: -0.1700
Data Index: 4581283 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6039. Min Range: -3.6039
Max Act: 3.2591. Min Act: -0.1700
Data Index: 5514048 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #19