Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4728 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3947. Min Range: -3.3947
Max Act: 3.3947. Min Act: -0.1700
Data Index: 554307 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3947. Min Range: -3.3947
Max Act: 3.3005. Min Act: -0.1700
Data Index: 4136075 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3947. Min Range: -3.3947
Max Act: 3.2220. Min Act: -0.1700
Data Index: 5901447 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3947. Min Range: -3.3947
Max Act: 3.1905. Min Act: -0.1700
Data Index: 7878356 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3947. Min Range: -3.3947
Max Act: 3.1748. Min Act: -0.1700
Data Index: 5034678 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3947. Min Range: -3.3947
Max Act: 3.1591. Min Act: -0.1700
Data Index: 5430283 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3947. Min Range: -3.3947
Max Act: 3.1433. Min Act: -0.1700
Data Index: 8824755 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3947. Min Range: -3.3947
Max Act: 3.1433. Min Act: -0.1700
Data Index: 6728066 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3947. Min Range: -3.3947
Max Act: 3.1433. Min Act: -0.1700
Data Index: 5025004 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3947. Min Range: -3.3947
Max Act: 3.1276. Min Act: -0.1700
Data Index: 5253033 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3947. Min Range: -3.3947
Max Act: 3.1433. Min Act: -0.1700
Data Index: 4971247 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3947. Min Range: -3.3947
Max Act: 3.1276. Min Act: -0.1700
Data Index: 6540441 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3947. Min Range: -3.3947
Max Act: 3.1118. Min Act: -0.1700
Data Index: 1654927 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3947. Min Range: -3.3947
Max Act: 3.1118. Min Act: -0.1700
Data Index: 6154107 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3947. Min Range: -3.3947
Max Act: 3.0803. Min Act: -0.1700
Data Index: 8270920 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3947. Min Range: -3.3947
Max Act: 3.0961. Min Act: -0.1700
Data Index: 5988672 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3947. Min Range: -3.3947
Max Act: 3.0803. Min Act: -0.1700
Data Index: 4275734 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3947. Min Range: -3.3947
Max Act: 3.0488. Min Act: -0.1700
Data Index: 5372624 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3947. Min Range: -3.3947
Max Act: 3.0645. Min Act: -0.1700
Data Index: 5618810 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3947. Min Range: -3.3947
Max Act: 3.0330. Min Act: -0.1700
Data Index: 5640682 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #19