Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4312 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4305. Min Range: -5.4305
Max Act: 5.4305. Min Act: -0.1700
Data Index: 7936057 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4305. Min Range: -5.4305
Max Act: 5.3993. Min Act: -0.1700
Data Index: 7525511 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4305. Min Range: -5.4305
Max Act: 5.3993. Min Act: -0.1700
Data Index: 3724177 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4305. Min Range: -5.4305
Max Act: 5.3993. Min Act: -0.1700
Data Index: 5329302 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4305. Min Range: -5.4305
Max Act: 5.3368. Min Act: -0.1700
Data Index: 8084221 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4305. Min Range: -5.4305
Max Act: 5.3055. Min Act: -0.1700
Data Index: 3649717 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4305. Min Range: -5.4305
Max Act: 5.3055. Min Act: -0.1700
Data Index: 7110755 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4305. Min Range: -5.4305
Max Act: 5.3055. Min Act: -0.1700
Data Index: 5942524 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4305. Min Range: -5.4305
Max Act: 5.2430. Min Act: -0.1700
Data Index: 5261094 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4305. Min Range: -5.4305
Max Act: 5.2430. Min Act: -0.1700
Data Index: 3826470 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4305. Min Range: -5.4305
Max Act: 5.2430. Min Act: -0.1700
Data Index: 3190831 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4305. Min Range: -5.4305
Max Act: 5.2430. Min Act: -0.1700
Data Index: 8659347 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4305. Min Range: -5.4305
Max Act: 5.2118. Min Act: -0.1700
Data Index: 3190830 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4305. Min Range: -5.4305
Max Act: 5.2118. Min Act: -0.1700
Data Index: 3326522 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4305. Min Range: -5.4305
Max Act: 5.1805. Min Act: -0.1700
Data Index: 473735 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4305. Min Range: -5.4305
Max Act: 5.1805. Min Act: -0.1700
Data Index: 7974212 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4305. Min Range: -5.4305
Max Act: 5.1805. Min Act: -0.1700
Data Index: 4315688 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4305. Min Range: -5.4305
Max Act: 5.1493. Min Act: -0.1700
Data Index: 3758289 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4305. Min Range: -5.4305
Max Act: 5.1180. Min Act: -0.1700
Data Index: 6035230 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4305. Min Range: -5.4305
Max Act: 5.1493. Min Act: -0.1700
Data Index: 841568 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #19