Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3252 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4934. Min Range: -7.4934
Max Act: 7.4622. Min Act: -0.1700
Data Index: 178626 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4934. Min Range: -7.4934
Max Act: 7.4934. Min Act: -0.1700
Data Index: 4464453 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4934. Min Range: -7.4934
Max Act: 7.3372. Min Act: -0.1700
Data Index: 4580808 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4934. Min Range: -7.4934
Max Act: 7.2747. Min Act: -0.1700
Data Index: 1368464 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4934. Min Range: -7.4934
Max Act: 7.2747. Min Act: -0.1700
Data Index: 1802749 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4934. Min Range: -7.4934
Max Act: 7.2747. Min Act: -0.1700
Data Index: 8621834 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4934. Min Range: -7.4934
Max Act: 7.2747. Min Act: -0.1700
Data Index: 11184 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4934. Min Range: -7.4934
Max Act: 7.2122. Min Act: -0.1700
Data Index: 774945 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4934. Min Range: -7.4934
Max Act: 7.1497. Min Act: -0.1700
Data Index: 2509194 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4934. Min Range: -7.4934
Max Act: 7.0559. Min Act: -0.1700
Data Index: 5567633 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4934. Min Range: -7.4934
Max Act: 7.0559. Min Act: -0.1700
Data Index: 2862257 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4934. Min Range: -7.4934
Max Act: 7.0559. Min Act: -0.1700
Data Index: 4952944 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4934. Min Range: -7.4934
Max Act: 7.0247. Min Act: -0.1700
Data Index: 3902261 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4934. Min Range: -7.4934
Max Act: 7.0247. Min Act: -0.1700
Data Index: 1291377 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4934. Min Range: -7.4934
Max Act: 7.0559. Min Act: -0.1700
Data Index: 4669466 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4934. Min Range: -7.4934
Max Act: 7.0247. Min Act: -0.1700
Data Index: 8648185 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4934. Min Range: -7.4934
Max Act: 6.9934. Min Act: -0.1700
Data Index: 495035 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4934. Min Range: -7.4934
Max Act: 6.9622. Min Act: -0.1700
Data Index: 3026084 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4934. Min Range: -7.4934
Max Act: 6.9309. Min Act: -0.1700
Data Index: 4120676 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4934. Min Range: -7.4934
Max Act: 6.9309. Min Act: -0.1700
Data Index: 2391542 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #19