Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3395 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7151. Min Range: -6.7151
Max Act: 6.7151. Min Act: -0.1700
Data Index: 8491467 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7151. Min Range: -6.7151
Max Act: 6.7151. Min Act: -0.1700
Data Index: 6318462 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7151. Min Range: -6.7151
Max Act: 6.6839. Min Act: -0.1700
Data Index: 666945 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7151. Min Range: -6.7151
Max Act: 6.5276. Min Act: -0.1700
Data Index: 651957 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7151. Min Range: -6.7151
Max Act: 6.4651. Min Act: -0.1700
Data Index: 1027714 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7151. Min Range: -6.7151
Max Act: 6.4339. Min Act: -0.1700
Data Index: 572048 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7151. Min Range: -6.7151
Max Act: 6.3714. Min Act: -0.1700
Data Index: 4746441 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7151. Min Range: -6.7151
Max Act: 6.3401. Min Act: -0.1700
Data Index: 3071451 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7151. Min Range: -6.7151
Max Act: 6.3401. Min Act: -0.1700
Data Index: 1904499 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7151. Min Range: -6.7151
Max Act: 6.3089. Min Act: -0.1700
Data Index: 530729 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7151. Min Range: -6.7151
Max Act: 6.2776. Min Act: -0.1700
Data Index: 8031680 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7151. Min Range: -6.7151
Max Act: 6.2776. Min Act: -0.1700
Data Index: 3838178 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7151. Min Range: -6.7151
Max Act: 6.2464. Min Act: -0.1700
Data Index: 4455688 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7151. Min Range: -6.7151
Max Act: 6.2464. Min Act: -0.1700
Data Index: 4050619 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7151. Min Range: -6.7151
Max Act: 6.2151. Min Act: -0.1700
Data Index: 4368389 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7151. Min Range: -6.7151
Max Act: 6.1839. Min Act: -0.1700
Data Index: 1651508 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7151. Min Range: -6.7151
Max Act: 6.2151. Min Act: -0.1700
Data Index: 4108296 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7151. Min Range: -6.7151
Max Act: 6.1839. Min Act: -0.1700
Data Index: 3263950 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7151. Min Range: -6.7151
Max Act: 6.1839. Min Act: -0.1700
Data Index: 5133868 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7151. Min Range: -6.7151
Max Act: 6.1839. Min Act: -0.1700
Data Index: 2214843 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #19