Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5768 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.4586. Min Range: -2.4586
Max Act: 2.4586. Min Act: -0.1700
Data Index: 3334930 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4586. Min Range: -2.4586
Max Act: 2.4261. Min Act: -0.1700
Data Index: 4497902 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4586. Min Range: -2.4586
Max Act: 2.4261. Min Act: -0.1700
Data Index: 2758768 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4586. Min Range: -2.4586
Max Act: 2.3771. Min Act: -0.1700
Data Index: 6299935 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4586. Min Range: -2.4586
Max Act: 2.3771. Min Act: -0.1700
Data Index: 8258428 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4586. Min Range: -2.4586
Max Act: 2.3607. Min Act: -0.1700
Data Index: 5981589 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4586. Min Range: -2.4586
Max Act: 2.3444. Min Act: -0.1700
Data Index: 1685158 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4586. Min Range: -2.4586
Max Act: 2.3444. Min Act: -0.1700
Data Index: 4328143 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4586. Min Range: -2.4586
Max Act: 2.3444. Min Act: -0.1700
Data Index: 1724221 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4586. Min Range: -2.4586
Max Act: 2.3280. Min Act: -0.1700
Data Index: 6417112 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4586. Min Range: -2.4586
Max Act: 2.2951. Min Act: -0.1700
Data Index: 5128515 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4586. Min Range: -2.4586
Max Act: 2.2786. Min Act: -0.1700
Data Index: 1157665 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4586. Min Range: -2.4586
Max Act: 2.2621. Min Act: -0.1700
Data Index: 1093302 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4586. Min Range: -2.4586
Max Act: 2.2456. Min Act: -0.1700
Data Index: 6171319 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4586. Min Range: -2.4586
Max Act: 2.2456. Min Act: -0.1700
Data Index: 5700228 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4586. Min Range: -2.4586
Max Act: 2.2456. Min Act: -0.1700
Data Index: 5312886 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4586. Min Range: -2.4586
Max Act: 2.2621. Min Act: -0.1700
Data Index: 7113096 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4586. Min Range: -2.4586
Max Act: 2.2291. Min Act: -0.1700
Data Index: 1119501 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4586. Min Range: -2.4586
Max Act: 2.2291. Min Act: -0.1700
Data Index: 1923961 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4586. Min Range: -2.4586
Max Act: 2.2125. Min Act: -0.1700
Data Index: 3837340 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #19