Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4858 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5887. Min Range: -5.5887
Max Act: 5.5887. Min Act: -0.1700
Data Index: 4144120 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5887. Min Range: -5.5887
Max Act: 5.4637. Min Act: -0.1700
Data Index: 4375580 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5887. Min Range: -5.5887
Max Act: 5.4012. Min Act: -0.1700
Data Index: 6773829 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5887. Min Range: -5.5887
Max Act: 5.3699. Min Act: -0.1700
Data Index: 3101731 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5887. Min Range: -5.5887
Max Act: 5.2762. Min Act: -0.1700
Data Index: 1782297 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5887. Min Range: -5.5887
Max Act: 5.2449. Min Act: -0.1700
Data Index: 4957286 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5887. Min Range: -5.5887
Max Act: 5.2137. Min Act: -0.1700
Data Index: 6357463 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5887. Min Range: -5.5887
Max Act: 5.1824. Min Act: -0.1700
Data Index: 5979381 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5887. Min Range: -5.5887
Max Act: 5.1824. Min Act: -0.1700
Data Index: 7003613 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5887. Min Range: -5.5887
Max Act: 5.0887. Min Act: -0.1700
Data Index: 7885923 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5887. Min Range: -5.5887
Max Act: 5.1199. Min Act: -0.1700
Data Index: 28728 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5887. Min Range: -5.5887
Max Act: 5.1199. Min Act: -0.1700
Data Index: 2271872 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5887. Min Range: -5.5887
Max Act: 5.0887. Min Act: -0.1700
Data Index: 4430523 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5887. Min Range: -5.5887
Max Act: 5.0887. Min Act: -0.1700
Data Index: 2639583 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5887. Min Range: -5.5887
Max Act: 5.0887. Min Act: -0.1700
Data Index: 4626408 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5887. Min Range: -5.5887
Max Act: 5.0887. Min Act: -0.1700
Data Index: 2752512 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5887. Min Range: -5.5887
Max Act: 5.0574. Min Act: -0.1700
Data Index: 95264 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5887. Min Range: -5.5887
Max Act: 5.0574. Min Act: -0.1700
Data Index: 4388676 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5887. Min Range: -5.5887
Max Act: 5.0262. Min Act: -0.1700
Data Index: 1406847 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5887. Min Range: -5.5887
Max Act: 5.0262. Min Act: -0.1700
Data Index: 6075163 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #19