Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 970 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8145. Min Range: -3.8145
Max Act: 3.8145. Min Act: -0.1700
Data Index: 1353307 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8145. Min Range: -3.8145
Max Act: 3.7520. Min Act: -0.1700
Data Index: 6720594 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8145. Min Range: -3.8145
Max Act: 3.6581. Min Act: -0.1700
Data Index: 1995858 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8145. Min Range: -3.8145
Max Act: 3.6268. Min Act: -0.1700
Data Index: 2562765 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8145. Min Range: -3.8145
Max Act: 3.5799. Min Act: -0.1700
Data Index: 7141372 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8145. Min Range: -3.8145
Max Act: 3.5172. Min Act: -0.1700
Data Index: 5390281 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8145. Min Range: -3.8145
Max Act: 3.5172. Min Act: -0.1700
Data Index: 5368646 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8145. Min Range: -3.8145
Max Act: 3.4546. Min Act: -0.1700
Data Index: 6076075 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8145. Min Range: -3.8145
Max Act: 3.4232. Min Act: -0.1700
Data Index: 3475125 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8145. Min Range: -3.8145
Max Act: 3.4232. Min Act: -0.1700
Data Index: 131549 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8145. Min Range: -3.8145
Max Act: 3.4389. Min Act: -0.1700
Data Index: 4376075 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8145. Min Range: -3.8145
Max Act: 3.4232. Min Act: -0.1700
Data Index: 3827970 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8145. Min Range: -3.8145
Max Act: 3.4232. Min Act: -0.1700
Data Index: 5105903 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8145. Min Range: -3.8145
Max Act: 3.4076. Min Act: -0.1700
Data Index: 636469 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8145. Min Range: -3.8145
Max Act: 3.4076. Min Act: -0.1700
Data Index: 8835 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8145. Min Range: -3.8145
Max Act: 3.4232. Min Act: -0.1700
Data Index: 8487104 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8145. Min Range: -3.8145
Max Act: 3.3919. Min Act: -0.1700
Data Index: 3742 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8145. Min Range: -3.8145
Max Act: 3.3919. Min Act: -0.1700
Data Index: 7173147 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8145. Min Range: -3.8145
Max Act: 3.3919. Min Act: -0.1700
Data Index: 636468 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8145. Min Range: -3.8145
Max Act: 3.3919. Min Act: -0.1700
Data Index: 4193527 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #19