Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1585 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.9997. Min Range: -2.9997
Max Act: 2.9997. Min Act: -0.1700
Data Index: 4740259 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9997. Min Range: -2.9997
Max Act: 2.9839. Min Act: -0.1700
Data Index: 2158300 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9997. Min Range: -2.9997
Max Act: 2.9681. Min Act: -0.1700
Data Index: 1069601 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9997. Min Range: -2.9997
Max Act: 2.8730. Min Act: -0.1700
Data Index: 1411152 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9997. Min Range: -2.9997
Max Act: 2.8254. Min Act: -0.1700
Data Index: 301549 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9997. Min Range: -2.9997
Max Act: 2.8254. Min Act: -0.1700
Data Index: 2951858 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9997. Min Range: -2.9997
Max Act: 2.8094. Min Act: -0.1700
Data Index: 6357059 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9997. Min Range: -2.9997
Max Act: 2.8094. Min Act: -0.1700
Data Index: 7931019 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9997. Min Range: -2.9997
Max Act: 2.7935. Min Act: -0.1700
Data Index: 4216212 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9997. Min Range: -2.9997
Max Act: 2.7776. Min Act: -0.1700
Data Index: 8724268 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9997. Min Range: -2.9997
Max Act: 2.7935. Min Act: -0.1700
Data Index: 4705762 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9997. Min Range: -2.9997
Max Act: 2.7616. Min Act: -0.1700
Data Index: 4835379 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9997. Min Range: -2.9997
Max Act: 2.7616. Min Act: -0.1700
Data Index: 8609597 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9997. Min Range: -2.9997
Max Act: 2.7935. Min Act: -0.1700
Data Index: 5290183 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9997. Min Range: -2.9997
Max Act: 2.7297. Min Act: -0.1700
Data Index: 8175178 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9997. Min Range: -2.9997
Max Act: 2.7137. Min Act: -0.1700
Data Index: 2152316 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9997. Min Range: -2.9997
Max Act: 2.6977. Min Act: -0.1700
Data Index: 6421722 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9997. Min Range: -2.9997
Max Act: 2.7297. Min Act: -0.1700
Data Index: 4740260 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9997. Min Range: -2.9997
Max Act: 2.7137. Min Act: -0.1700
Data Index: 2028228 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9997. Min Range: -2.9997
Max Act: 2.6817. Min Act: -0.1700
Data Index: 3037968 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #19