Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 996 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1756. Min Range: -5.1756
Max Act: 5.1756. Min Act: -0.1700
Data Index: 3701204 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1756. Min Range: -5.1756
Max Act: 4.9881. Min Act: -0.1700
Data Index: 240018 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1756. Min Range: -5.1756
Max Act: 4.8943. Min Act: -0.1700
Data Index: 4041182 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1756. Min Range: -5.1756
Max Act: 4.8318. Min Act: -0.1700
Data Index: 7497598 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1756. Min Range: -5.1756
Max Act: 4.8943. Min Act: -0.1700
Data Index: 4626912 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1756. Min Range: -5.1756
Max Act: 4.7693. Min Act: -0.1700
Data Index: 6097616 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1756. Min Range: -5.1756
Max Act: 4.7693. Min Act: -0.1700
Data Index: 8523643 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1756. Min Range: -5.1756
Max Act: 4.7381. Min Act: -0.1700
Data Index: 164783 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1756. Min Range: -5.1756
Max Act: 4.7068. Min Act: -0.1700
Data Index: 5524516 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1756. Min Range: -5.1756
Max Act: 4.6756. Min Act: -0.1700
Data Index: 3699412 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1756. Min Range: -5.1756
Max Act: 4.6756. Min Act: -0.1700
Data Index: 6480092 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1756. Min Range: -5.1756
Max Act: 4.6756. Min Act: -0.1700
Data Index: 3024895 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1756. Min Range: -5.1756
Max Act: 4.6443. Min Act: -0.1700
Data Index: 7628306 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1756. Min Range: -5.1756
Max Act: 4.6443. Min Act: -0.1700
Data Index: 8339206 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1756. Min Range: -5.1756
Max Act: 4.6443. Min Act: -0.1700
Data Index: 4877436 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1756. Min Range: -5.1756
Max Act: 4.6131. Min Act: -0.1700
Data Index: 4187264 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1756. Min Range: -5.1756
Max Act: 4.6131. Min Act: -0.1700
Data Index: 6884649 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1756. Min Range: -5.1756
Max Act: 4.6131. Min Act: -0.1700
Data Index: 3355062 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1756. Min Range: -5.1756
Max Act: 4.6131. Min Act: -0.1700
Data Index: 1170220 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1756. Min Range: -5.1756
Max Act: 4.5818. Min Act: -0.1700
Data Index: 3010061 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #19