Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3532 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5197. Min Range: -5.5197
Max Act: 5.5197. Min Act: -0.1700
Data Index: 2159515 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5197. Min Range: -5.5197
Max Act: 5.4884. Min Act: -0.1700
Data Index: 3271145 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5197. Min Range: -5.5197
Max Act: 5.4884. Min Act: -0.1700
Data Index: 5062362 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5197. Min Range: -5.5197
Max Act: 5.4572. Min Act: -0.1700
Data Index: 2069456 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5197. Min Range: -5.5197
Max Act: 5.4259. Min Act: -0.1700
Data Index: 1818232 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5197. Min Range: -5.5197
Max Act: 5.4259. Min Act: -0.1700
Data Index: 5162648 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5197. Min Range: -5.5197
Max Act: 5.4259. Min Act: -0.1700
Data Index: 6596256 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5197. Min Range: -5.5197
Max Act: 5.4259. Min Act: -0.1700
Data Index: 4952731 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5197. Min Range: -5.5197
Max Act: 5.3634. Min Act: -0.1700
Data Index: 855536 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5197. Min Range: -5.5197
Max Act: 5.3947. Min Act: -0.1700
Data Index: 6718327 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5197. Min Range: -5.5197
Max Act: 5.3634. Min Act: -0.1700
Data Index: 7260921 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5197. Min Range: -5.5197
Max Act: 5.3322. Min Act: -0.1700
Data Index: 7408551 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5197. Min Range: -5.5197
Max Act: 5.3322. Min Act: -0.1700
Data Index: 2230266 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5197. Min Range: -5.5197
Max Act: 5.3322. Min Act: -0.1700
Data Index: 255159 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5197. Min Range: -5.5197
Max Act: 5.3322. Min Act: -0.1700
Data Index: 1725057 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5197. Min Range: -5.5197
Max Act: 5.3322. Min Act: -0.1700
Data Index: 8444442 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5197. Min Range: -5.5197
Max Act: 5.3634. Min Act: -0.1700
Data Index: 8420428 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5197. Min Range: -5.5197
Max Act: 5.3322. Min Act: -0.1700
Data Index: 1339157 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5197. Min Range: -5.5197
Max Act: 5.3009. Min Act: -0.1700
Data Index: 4831802 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5197. Min Range: -5.5197
Max Act: 5.3009. Min Act: -0.1700
Data Index: 2296451 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #19