Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5918 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7944. Min Range: -4.7944
Max Act: 4.7944. Min Act: -0.1700
Data Index: 4826495 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7944. Min Range: -4.7944
Max Act: 4.6694. Min Act: -0.1700
Data Index: 8670346 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7944. Min Range: -4.7944
Max Act: 4.6382. Min Act: -0.1700
Data Index: 6274162 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7944. Min Range: -4.7944
Max Act: 4.6069. Min Act: -0.1700
Data Index: 6846771 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7944. Min Range: -4.7944
Max Act: 4.5757. Min Act: -0.1700
Data Index: 1681904 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7944. Min Range: -4.7944
Max Act: 4.5757. Min Act: -0.1700
Data Index: 1681905 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7944. Min Range: -4.7944
Max Act: 4.5444. Min Act: -0.1700
Data Index: 7046287 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7944. Min Range: -4.7944
Max Act: 4.5132. Min Act: -0.1700
Data Index: 8603615 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7944. Min Range: -4.7944
Max Act: 4.5444. Min Act: -0.1700
Data Index: 6115731 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7944. Min Range: -4.7944
Max Act: 4.5444. Min Act: -0.1700
Data Index: 2739757 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7944. Min Range: -4.7944
Max Act: 4.5132. Min Act: -0.1700
Data Index: 6990497 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7944. Min Range: -4.7944
Max Act: 4.5132. Min Act: -0.1700
Data Index: 5044606 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7944. Min Range: -4.7944
Max Act: 4.5132. Min Act: -0.1700
Data Index: 4826503 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7944. Min Range: -4.7944
Max Act: 4.5132. Min Act: -0.1700
Data Index: 2913908 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7944. Min Range: -4.7944
Max Act: 4.4819. Min Act: -0.1700
Data Index: 3225628 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7944. Min Range: -4.7944
Max Act: 4.5132. Min Act: -0.1700
Data Index: 3077689 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7944. Min Range: -4.7944
Max Act: 4.5132. Min Act: -0.1700
Data Index: 8726990 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7944. Min Range: -4.7944
Max Act: 4.5132. Min Act: -0.1700
Data Index: 7038137 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7944. Min Range: -4.7944
Max Act: 4.5132. Min Act: -0.1700
Data Index: 1883959 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7944. Min Range: -4.7944
Max Act: 4.4507. Min Act: -0.1700
Data Index: 3943340 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #19