Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3126 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2212. Min Range: -7.2212
Max Act: 7.2212. Min Act: -0.1700
Data Index: 3409781 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2212. Min Range: -7.2212
Max Act: 7.0649. Min Act: -0.1700
Data Index: 1404403 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2212. Min Range: -7.2212
Max Act: 7.0649. Min Act: -0.1700
Data Index: 6430530 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2212. Min Range: -7.2212
Max Act: 7.0649. Min Act: -0.1700
Data Index: 5182425 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2212. Min Range: -7.2212
Max Act: 7.0024. Min Act: -0.1700
Data Index: 6686781 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2212. Min Range: -7.2212
Max Act: 7.0024. Min Act: -0.1700
Data Index: 3736403 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2212. Min Range: -7.2212
Max Act: 6.9712. Min Act: -0.1700
Data Index: 4113080 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2212. Min Range: -7.2212
Max Act: 6.9399. Min Act: -0.1700
Data Index: 4797389 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2212. Min Range: -7.2212
Max Act: 6.9087. Min Act: -0.1700
Data Index: 1259078 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2212. Min Range: -7.2212
Max Act: 6.8462. Min Act: -0.1700
Data Index: 2259697 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2212. Min Range: -7.2212
Max Act: 6.8462. Min Act: -0.1700
Data Index: 6509542 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2212. Min Range: -7.2212
Max Act: 6.8149. Min Act: -0.1700
Data Index: 8041986 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2212. Min Range: -7.2212
Max Act: 6.8149. Min Act: -0.1700
Data Index: 4700539 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2212. Min Range: -7.2212
Max Act: 6.8149. Min Act: -0.1700
Data Index: 2858213 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2212. Min Range: -7.2212
Max Act: 6.7837. Min Act: -0.1700
Data Index: 1273985 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2212. Min Range: -7.2212
Max Act: 6.7837. Min Act: -0.1700
Data Index: 7215184 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2212. Min Range: -7.2212
Max Act: 6.7524. Min Act: -0.1700
Data Index: 5512051 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2212. Min Range: -7.2212
Max Act: 6.7524. Min Act: -0.1700
Data Index: 2861217 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2212. Min Range: -7.2212
Max Act: 6.7524. Min Act: -0.1700
Data Index: 4912092 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2212. Min Range: -7.2212
Max Act: 6.7524. Min Act: -0.1700
Data Index: 5271336 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #19