Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 260 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5695. Min Range: -9.5695
Max Act: 9.5695. Min Act: -0.1700
Data Index: 4709167 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5695. Min Range: -9.5695
Max Act: 9.4445. Min Act: -0.1700
Data Index: 2938339 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5695. Min Range: -9.5695
Max Act: 9.4445. Min Act: -0.1700
Data Index: 1802920 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5695. Min Range: -9.5695
Max Act: 9.3820. Min Act: -0.1700
Data Index: 8384017 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5695. Min Range: -9.5695
Max Act: 9.2570. Min Act: -0.1700
Data Index: 3477457 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5695. Min Range: -9.5695
Max Act: 9.2570. Min Act: -0.1700
Data Index: 8561869 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5695. Min Range: -9.5695
Max Act: 9.1945. Min Act: -0.1700
Data Index: 3993956 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5695. Min Range: -9.5695
Max Act: 9.1945. Min Act: -0.1700
Data Index: 6302041 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5695. Min Range: -9.5695
Max Act: 9.1320. Min Act: -0.1700
Data Index: 4332685 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5695. Min Range: -9.5695
Max Act: 9.1320. Min Act: -0.1700
Data Index: 1565878 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5695. Min Range: -9.5695
Max Act: 9.1320. Min Act: -0.1700
Data Index: 6860195 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5695. Min Range: -9.5695
Max Act: 9.1320. Min Act: -0.1700
Data Index: 3151338 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5695. Min Range: -9.5695
Max Act: 9.1320. Min Act: -0.1700
Data Index: 3161577 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5695. Min Range: -9.5695
Max Act: 9.1320. Min Act: -0.1700
Data Index: 4138065 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5695. Min Range: -9.5695
Max Act: 9.0695. Min Act: -0.1700
Data Index: 6669229 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5695. Min Range: -9.5695
Max Act: 9.0695. Min Act: -0.1700
Data Index: 4732543 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5695. Min Range: -9.5695
Max Act: 8.9445. Min Act: -0.1700
Data Index: 2633896 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5695. Min Range: -9.5695
Max Act: 8.9445. Min Act: -0.1700
Data Index: 1312340 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5695. Min Range: -9.5695
Max Act: 8.8820. Min Act: -0.1700
Data Index: 6926862 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5695. Min Range: -9.5695
Max Act: 8.8820. Min Act: -0.1700
Data Index: 5165923 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #19