Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 356 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5314. Min Range: -4.5314
Max Act: 4.5314. Min Act: -0.1700
Data Index: 7038047 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5314. Min Range: -4.5314
Max Act: 4.5314. Min Act: -0.1700
Data Index: 609706 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5314. Min Range: -4.5314
Max Act: 4.4689. Min Act: -0.1700
Data Index: 8009153 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5314. Min Range: -4.5314
Max Act: 4.4689. Min Act: -0.1700
Data Index: 6306645 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5314. Min Range: -4.5314
Max Act: 4.4377. Min Act: -0.1700
Data Index: 510003 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5314. Min Range: -4.5314
Max Act: 4.4064. Min Act: -0.1700
Data Index: 5568344 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5314. Min Range: -4.5314
Max Act: 4.3752. Min Act: -0.1700
Data Index: 309247 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5314. Min Range: -4.5314
Max Act: 4.3752. Min Act: -0.1700
Data Index: 3946116 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5314. Min Range: -4.5314
Max Act: 4.3752. Min Act: -0.1700
Data Index: 558729 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5314. Min Range: -4.5314
Max Act: 4.3127. Min Act: -0.1700
Data Index: 5562103 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5314. Min Range: -4.5314
Max Act: 4.2814. Min Act: -0.1700
Data Index: 4930147 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5314. Min Range: -4.5314
Max Act: 4.3127. Min Act: -0.1700
Data Index: 7173579 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5314. Min Range: -4.5314
Max Act: 4.2501. Min Act: -0.1700
Data Index: 8358292 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5314. Min Range: -4.5314
Max Act: 4.2814. Min Act: -0.1700
Data Index: 5390825 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5314. Min Range: -4.5314
Max Act: 4.2814. Min Act: -0.1700
Data Index: 6971101 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5314. Min Range: -4.5314
Max Act: 4.2501. Min Act: -0.1700
Data Index: 5641688 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5314. Min Range: -4.5314
Max Act: 4.2189. Min Act: -0.1700
Data Index: 6869909 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5314. Min Range: -4.5314
Max Act: 4.2501. Min Act: -0.1700
Data Index: 4386168 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5314. Min Range: -4.5314
Max Act: 4.2501. Min Act: -0.1700
Data Index: 4292962 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5314. Min Range: -4.5314
Max Act: 4.2189. Min Act: -0.1700
Data Index: 3027449 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #19