Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3100 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2969. Min Range: -6.2969
Max Act: 6.2969. Min Act: -0.1700
Data Index: 822301 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2969. Min Range: -6.2969
Max Act: 6.1719. Min Act: -0.1700
Data Index: 8647140 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2969. Min Range: -6.2969
Max Act: 6.1719. Min Act: -0.1700
Data Index: 3021293 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2969. Min Range: -6.2969
Max Act: 6.1407. Min Act: -0.1700
Data Index: 2276866 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2969. Min Range: -6.2969
Max Act: 6.0782. Min Act: -0.1700
Data Index: 3408721 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2969. Min Range: -6.2969
Max Act: 6.0157. Min Act: -0.1700
Data Index: 4046290 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2969. Min Range: -6.2969
Max Act: 6.0157. Min Act: -0.1700
Data Index: 5598817 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2969. Min Range: -6.2969
Max Act: 5.9844. Min Act: -0.1700
Data Index: 1866262 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2969. Min Range: -6.2969
Max Act: 5.9844. Min Act: -0.1700
Data Index: 5782855 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2969. Min Range: -6.2969
Max Act: 5.9532. Min Act: -0.1700
Data Index: 24866 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2969. Min Range: -6.2969
Max Act: 5.9532. Min Act: -0.1700
Data Index: 5633986 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2969. Min Range: -6.2969
Max Act: 5.8907. Min Act: -0.1700
Data Index: 5129491 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2969. Min Range: -6.2969
Max Act: 5.9219. Min Act: -0.1700
Data Index: 4093446 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2969. Min Range: -6.2969
Max Act: 5.8907. Min Act: -0.1700
Data Index: 4243218 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2969. Min Range: -6.2969
Max Act: 5.9219. Min Act: -0.1700
Data Index: 8814555 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2969. Min Range: -6.2969
Max Act: 5.8594. Min Act: -0.1700
Data Index: 5500575 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2969. Min Range: -6.2969
Max Act: 5.8282. Min Act: -0.1700
Data Index: 3870207 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2969. Min Range: -6.2969
Max Act: 5.7969. Min Act: -0.1700
Data Index: 1493177 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2969. Min Range: -6.2969
Max Act: 5.7969. Min Act: -0.1700
Data Index: 526955 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2969. Min Range: -6.2969
Max Act: 5.7969. Min Act: -0.1700
Data Index: 4792486 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #19