Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5811 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6583. Min Range: -3.6583
Max Act: 3.6583. Min Act: -0.1700
Data Index: 2594604 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6583. Min Range: -3.6583
Max Act: 3.6427. Min Act: -0.1700
Data Index: 4977100 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6583. Min Range: -3.6583
Max Act: 3.6114. Min Act: -0.1700
Data Index: 8480292 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6583. Min Range: -3.6583
Max Act: 3.5957. Min Act: -0.1700
Data Index: 144858 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6583. Min Range: -3.6583
Max Act: 3.5801. Min Act: -0.1700
Data Index: 8311399 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6583. Min Range: -3.6583
Max Act: 3.5801. Min Act: -0.1700
Data Index: 3831610 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6583. Min Range: -3.6583
Max Act: 3.5644. Min Act: -0.1700
Data Index: 7105940 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6583. Min Range: -3.6583
Max Act: 3.5644. Min Act: -0.1700
Data Index: 7267213 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6583. Min Range: -3.6583
Max Act: 3.5957. Min Act: -0.1700
Data Index: 7767 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6583. Min Range: -3.6583
Max Act: 3.5487. Min Act: -0.1700
Data Index: 7105941 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6583. Min Range: -3.6583
Max Act: 3.5644. Min Act: -0.1700
Data Index: 3020101 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6583. Min Range: -3.6583
Max Act: 3.5331. Min Act: -0.1700
Data Index: 6589359 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6583. Min Range: -3.6583
Max Act: 3.5487. Min Act: -0.1700
Data Index: 8394555 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6583. Min Range: -3.6583
Max Act: 3.5331. Min Act: -0.1700
Data Index: 6630997 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6583. Min Range: -3.6583
Max Act: 3.5331. Min Act: -0.1700
Data Index: 3060881 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6583. Min Range: -3.6583
Max Act: 3.5018. Min Act: -0.1700
Data Index: 4715890 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6583. Min Range: -3.6583
Max Act: 3.5018. Min Act: -0.1700
Data Index: 5646059 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6583. Min Range: -3.6583
Max Act: 3.4861. Min Act: -0.1700
Data Index: 3789488 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6583. Min Range: -3.6583
Max Act: 3.5018. Min Act: -0.1700
Data Index: 929936 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6583. Min Range: -3.6583
Max Act: 3.4861. Min Act: -0.1700
Data Index: 2352518 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #19