Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3276 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5907. Min Range: -4.5907
Max Act: 4.5907. Min Act: -0.1700
Data Index: 7984399 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5907. Min Range: -4.5907
Max Act: 4.5595. Min Act: -0.1700
Data Index: 5352050 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5907. Min Range: -4.5907
Max Act: 4.5595. Min Act: -0.1700
Data Index: 8455048 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5907. Min Range: -4.5907
Max Act: 4.4657. Min Act: -0.1700
Data Index: 2703555 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5907. Min Range: -4.5907
Max Act: 4.4032. Min Act: -0.1700
Data Index: 2768489 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5907. Min Range: -4.5907
Max Act: 4.4032. Min Act: -0.1700
Data Index: 4597458 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5907. Min Range: -4.5907
Max Act: 4.4032. Min Act: -0.1700
Data Index: 4182617 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5907. Min Range: -4.5907
Max Act: 4.3719. Min Act: -0.1700
Data Index: 4387357 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5907. Min Range: -4.5907
Max Act: 4.3719. Min Act: -0.1700
Data Index: 8655327 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5907. Min Range: -4.5907
Max Act: 4.3407. Min Act: -0.1700
Data Index: 8243878 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5907. Min Range: -4.5907
Max Act: 4.3407. Min Act: -0.1700
Data Index: 5034055 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5907. Min Range: -4.5907
Max Act: 4.3407. Min Act: -0.1700
Data Index: 8484777 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5907. Min Range: -4.5907
Max Act: 4.3407. Min Act: -0.1700
Data Index: 1339613 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5907. Min Range: -4.5907
Max Act: 4.3407. Min Act: -0.1700
Data Index: 2844820 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5907. Min Range: -4.5907
Max Act: 4.3094. Min Act: -0.1700
Data Index: 7871151 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5907. Min Range: -4.5907
Max Act: 4.3094. Min Act: -0.1700
Data Index: 4951211 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5907. Min Range: -4.5907
Max Act: 4.3094. Min Act: -0.1700
Data Index: 2921975 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5907. Min Range: -4.5907
Max Act: 4.2782. Min Act: -0.1700
Data Index: 340682 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5907. Min Range: -4.5907
Max Act: 4.2782. Min Act: -0.1700
Data Index: 3221098 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5907. Min Range: -4.5907
Max Act: 4.2782. Min Act: -0.1700
Data Index: 1887422 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #19