Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4546 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1196. Min Range: -5.1196
Max Act: 5.0884. Min Act: -0.1700
Data Index: 1975587 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1196. Min Range: -5.1196
Max Act: 5.1196. Min Act: -0.1700
Data Index: 3122702 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1196. Min Range: -5.1196
Max Act: 5.0259. Min Act: -0.1700
Data Index: 7905095 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1196. Min Range: -5.1196
Max Act: 4.9946. Min Act: -0.1700
Data Index: 657817 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1196. Min Range: -5.1196
Max Act: 5.0259. Min Act: -0.1700
Data Index: 2472589 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1196. Min Range: -5.1196
Max Act: 4.9634. Min Act: -0.1700
Data Index: 6150144 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1196. Min Range: -5.1196
Max Act: 4.9321. Min Act: -0.1700
Data Index: 220245 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1196. Min Range: -5.1196
Max Act: 4.9321. Min Act: -0.1700
Data Index: 4351638 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1196. Min Range: -5.1196
Max Act: 4.9009. Min Act: -0.1700
Data Index: 2563240 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1196. Min Range: -5.1196
Max Act: 4.9009. Min Act: -0.1700
Data Index: 3017342 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1196. Min Range: -5.1196
Max Act: 4.9009. Min Act: -0.1700
Data Index: 8760082 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1196. Min Range: -5.1196
Max Act: 4.9009. Min Act: -0.1700
Data Index: 6109976 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1196. Min Range: -5.1196
Max Act: 4.8071. Min Act: -0.1700
Data Index: 4367083 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1196. Min Range: -5.1196
Max Act: 4.8384. Min Act: -0.1700
Data Index: 986271 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1196. Min Range: -5.1196
Max Act: 4.8384. Min Act: -0.1700
Data Index: 2114586 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1196. Min Range: -5.1196
Max Act: 4.8071. Min Act: -0.1700
Data Index: 4733303 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1196. Min Range: -5.1196
Max Act: 4.8071. Min Act: -0.1700
Data Index: 905519 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1196. Min Range: -5.1196
Max Act: 4.8071. Min Act: -0.1700
Data Index: 6558575 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1196. Min Range: -5.1196
Max Act: 4.8071. Min Act: -0.1700
Data Index: 1342207 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1196. Min Range: -5.1196
Max Act: 4.8071. Min Act: -0.1700
Data Index: 5113216 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #19