Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4050 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0961. Min Range: -6.0961
Max Act: 6.0961. Min Act: -0.1700
Data Index: 2717193 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0961. Min Range: -6.0961
Max Act: 6.0023. Min Act: -0.1700
Data Index: 2868208 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0961. Min Range: -6.0961
Max Act: 5.9711. Min Act: -0.1700
Data Index: 5965542 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0961. Min Range: -6.0961
Max Act: 5.9086. Min Act: -0.1700
Data Index: 1819713 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0961. Min Range: -6.0961
Max Act: 5.8148. Min Act: -0.1700
Data Index: 6832138 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0961. Min Range: -6.0961
Max Act: 5.7523. Min Act: -0.1700
Data Index: 7996290 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0961. Min Range: -6.0961
Max Act: 5.7523. Min Act: -0.1700
Data Index: 5470634 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0961. Min Range: -6.0961
Max Act: 5.7523. Min Act: -0.1700
Data Index: 6766612 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0961. Min Range: -6.0961
Max Act: 5.6898. Min Act: -0.1700
Data Index: 2513318 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0961. Min Range: -6.0961
Max Act: 5.6898. Min Act: -0.1700
Data Index: 5648158 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0961. Min Range: -6.0961
Max Act: 5.6898. Min Act: -0.1700
Data Index: 1408007 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0961. Min Range: -6.0961
Max Act: 5.6898. Min Act: -0.1700
Data Index: 1127946 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0961. Min Range: -6.0961
Max Act: 5.6586. Min Act: -0.1700
Data Index: 4711640 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0961. Min Range: -6.0961
Max Act: 5.6273. Min Act: -0.1700
Data Index: 967430 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0961. Min Range: -6.0961
Max Act: 5.6273. Min Act: -0.1700
Data Index: 3711058 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0961. Min Range: -6.0961
Max Act: 5.6273. Min Act: -0.1700
Data Index: 4392535 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0961. Min Range: -6.0961
Max Act: 5.5648. Min Act: -0.1700
Data Index: 6129158 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0961. Min Range: -6.0961
Max Act: 5.5648. Min Act: -0.1700
Data Index: 4638563 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0961. Min Range: -6.0961
Max Act: 5.5961. Min Act: -0.1700
Data Index: 3446282 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0961. Min Range: -6.0961
Max Act: 5.5648. Min Act: -0.1700
Data Index: 3645141 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #19