Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3934 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2963. Min Range: -3.2963
Max Act: 3.2963. Min Act: -0.1700
Data Index: 4050198 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2963. Min Range: -3.2963
Max Act: 3.2963. Min Act: -0.1700
Data Index: 3509423 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2963. Min Range: -3.2963
Max Act: 3.2963. Min Act: -0.1700
Data Index: 4005781 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2963. Min Range: -3.2963
Max Act: 3.2649. Min Act: -0.1700
Data Index: 845112 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2963. Min Range: -3.2963
Max Act: 3.2649. Min Act: -0.1700
Data Index: 1689038 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2963. Min Range: -3.2963
Max Act: 3.2334. Min Act: -0.1700
Data Index: 5720723 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2963. Min Range: -3.2963
Max Act: 3.2334. Min Act: -0.1700
Data Index: 2279420 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2963. Min Range: -3.2963
Max Act: 3.2334. Min Act: -0.1700
Data Index: 6226396 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2963. Min Range: -3.2963
Max Act: 3.2334. Min Act: -0.1700
Data Index: 2377540 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2963. Min Range: -3.2963
Max Act: 3.2334. Min Act: -0.1700
Data Index: 3336388 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2963. Min Range: -3.2963
Max Act: 3.2334. Min Act: -0.1700
Data Index: 1487322 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2963. Min Range: -3.2963
Max Act: 3.2334. Min Act: -0.1700
Data Index: 4217793 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2963. Min Range: -3.2963
Max Act: 3.2334. Min Act: -0.1700
Data Index: 3525068 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2963. Min Range: -3.2963
Max Act: 3.2334. Min Act: -0.1700
Data Index: 3997194 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2963. Min Range: -3.2963
Max Act: 3.2334. Min Act: -0.1700
Data Index: 994605 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2963. Min Range: -3.2963
Max Act: 3.2334. Min Act: -0.1700
Data Index: 6698520 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2963. Min Range: -3.2963
Max Act: 3.2334. Min Act: -0.1700
Data Index: 7420951 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2963. Min Range: -3.2963
Max Act: 3.2334. Min Act: -0.1700
Data Index: 7646269 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2963. Min Range: -3.2963
Max Act: 3.2334. Min Act: -0.1700
Data Index: 7975347 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2963. Min Range: -3.2963
Max Act: 3.2334. Min Act: -0.1700
Data Index: 3118649 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19