Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2053 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7009. Min Range: -9.7009
Max Act: 9.7009. Min Act: -0.1700
Data Index: 4438935 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7009. Min Range: -9.7009
Max Act: 9.0759. Min Act: -0.1700
Data Index: 3284216 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7009. Min Range: -9.7009
Max Act: 9.0134. Min Act: -0.1700
Data Index: 7187958 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7009. Min Range: -9.7009
Max Act: 9.0134. Min Act: -0.1700
Data Index: 1618862 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7009. Min Range: -9.7009
Max Act: 9.0134. Min Act: -0.1700
Data Index: 4253030 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7009. Min Range: -9.7009
Max Act: 9.0134. Min Act: -0.1700
Data Index: 4271716 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7009. Min Range: -9.7009
Max Act: 9.0134. Min Act: -0.1700
Data Index: 509184 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7009. Min Range: -9.7009
Max Act: 8.8259. Min Act: -0.1700
Data Index: 135793 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7009. Min Range: -9.7009
Max Act: 8.8259. Min Act: -0.1700
Data Index: 7191014 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7009. Min Range: -9.7009
Max Act: 8.8259. Min Act: -0.1700
Data Index: 8164731 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7009. Min Range: -9.7009
Max Act: 8.8259. Min Act: -0.1700
Data Index: 2041721 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7009. Min Range: -9.7009
Max Act: 8.8259. Min Act: -0.1700
Data Index: 8254039 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7009. Min Range: -9.7009
Max Act: 8.8259. Min Act: -0.1700
Data Index: 2559562 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7009. Min Range: -9.7009
Max Act: 8.8259. Min Act: -0.1700
Data Index: 4598369 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7009. Min Range: -9.7009
Max Act: 8.8259. Min Act: -0.1700
Data Index: 55516 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7009. Min Range: -9.7009
Max Act: 8.7634. Min Act: -0.1700
Data Index: 2233743 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7009. Min Range: -9.7009
Max Act: 8.7634. Min Act: -0.1700
Data Index: 8164730 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7009. Min Range: -9.7009
Max Act: 8.7009. Min Act: -0.1700
Data Index: 5339948 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7009. Min Range: -9.7009
Max Act: 8.7009. Min Act: -0.1700
Data Index: 4384310 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7009. Min Range: -9.7009
Max Act: 8.7009. Min Act: -0.1700
Data Index: 7128042 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #19