Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3908 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3922. Min Range: -9.3922
Max Act: 9.3922. Min Act: -0.1700
Data Index: 7869450 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3922. Min Range: -9.3922
Max Act: 9.2672. Min Act: -0.1700
Data Index: 6088831 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3922. Min Range: -9.3922
Max Act: 8.8922. Min Act: -0.1700
Data Index: 6087451 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3922. Min Range: -9.3922
Max Act: 8.7672. Min Act: -0.1700
Data Index: 7285037 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3922. Min Range: -9.3922
Max Act: 8.8297. Min Act: -0.1700
Data Index: 8749322 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3922. Min Range: -9.3922
Max Act: 8.7047. Min Act: -0.1700
Data Index: 6426876 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3922. Min Range: -9.3922
Max Act: 8.6422. Min Act: -0.1700
Data Index: 7742851 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3922. Min Range: -9.3922
Max Act: 8.6422. Min Act: -0.1700
Data Index: 2229341 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3922. Min Range: -9.3922
Max Act: 8.5172. Min Act: -0.1700
Data Index: 6939907 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3922. Min Range: -9.3922
Max Act: 8.5172. Min Act: -0.1700
Data Index: 2741900 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3922. Min Range: -9.3922
Max Act: 8.4547. Min Act: -0.1700
Data Index: 6758302 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3922. Min Range: -9.3922
Max Act: 8.4547. Min Act: -0.1700
Data Index: 774750 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3922. Min Range: -9.3922
Max Act: 8.4547. Min Act: -0.1700
Data Index: 7096974 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3922. Min Range: -9.3922
Max Act: 8.3922. Min Act: -0.1700
Data Index: 4119068 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3922. Min Range: -9.3922
Max Act: 8.3297. Min Act: -0.1700
Data Index: 4497878 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3922. Min Range: -9.3922
Max Act: 8.2672. Min Act: -0.1700
Data Index: 2620296 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3922. Min Range: -9.3922
Max Act: 8.2672. Min Act: -0.1700
Data Index: 1773776 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3922. Min Range: -9.3922
Max Act: 8.2047. Min Act: -0.1700
Data Index: 1866169 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3922. Min Range: -9.3922
Max Act: 8.2047. Min Act: -0.1700
Data Index: 5492474 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3922. Min Range: -9.3922
Max Act: 8.2047. Min Act: -0.1700
Data Index: 6123420 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #19