Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2733 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8144. Min Range: -7.8144
Max Act: 7.8144. Min Act: -0.1700
Data Index: 5020192 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8144. Min Range: -7.8144
Max Act: 7.5957. Min Act: -0.1700
Data Index: 6756086 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8144. Min Range: -7.8144
Max Act: 7.5019. Min Act: -0.1700
Data Index: 8342172 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8144. Min Range: -7.8144
Max Act: 7.5019. Min Act: -0.1700
Data Index: 6051309 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8144. Min Range: -7.8144
Max Act: 7.4707. Min Act: -0.1700
Data Index: 2775836 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8144. Min Range: -7.8144
Max Act: 7.3457. Min Act: -0.1700
Data Index: 3193686 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8144. Min Range: -7.8144
Max Act: 7.3457. Min Act: -0.1700
Data Index: 4597199 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8144. Min Range: -7.8144
Max Act: 7.3457. Min Act: -0.1700
Data Index: 540230 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8144. Min Range: -7.8144
Max Act: 7.3144. Min Act: -0.1700
Data Index: 7788373 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8144. Min Range: -7.8144
Max Act: 7.2832. Min Act: -0.1700
Data Index: 1771594 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8144. Min Range: -7.8144
Max Act: 7.2832. Min Act: -0.1700
Data Index: 1168913 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8144. Min Range: -7.8144
Max Act: 7.2832. Min Act: -0.1700
Data Index: 242661 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8144. Min Range: -7.8144
Max Act: 7.2832. Min Act: -0.1700
Data Index: 5767215 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8144. Min Range: -7.8144
Max Act: 7.2519. Min Act: -0.1700
Data Index: 2466428 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8144. Min Range: -7.8144
Max Act: 7.2519. Min Act: -0.1700
Data Index: 7566991 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8144. Min Range: -7.8144
Max Act: 7.2519. Min Act: -0.1700
Data Index: 4484341 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8144. Min Range: -7.8144
Max Act: 7.2519. Min Act: -0.1700
Data Index: 6550913 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8144. Min Range: -7.8144
Max Act: 7.2519. Min Act: -0.1700
Data Index: 4067209 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8144. Min Range: -7.8144
Max Act: 7.2207. Min Act: -0.1700
Data Index: 4785518 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8144. Min Range: -7.8144
Max Act: 7.2519. Min Act: -0.1700
Data Index: 777799 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #19