Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 703 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8535. Min Range: -4.8535
Max Act: 4.8535. Min Act: -0.1700
Data Index: 1623228 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8535. Min Range: -4.8535
Max Act: 4.6972. Min Act: -0.1700
Data Index: 1277157 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8535. Min Range: -4.8535
Max Act: 4.6972. Min Act: -0.1700
Data Index: 5251264 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8535. Min Range: -4.8535
Max Act: 4.6972. Min Act: -0.1700
Data Index: 999610 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8535. Min Range: -4.8535
Max Act: 4.6660. Min Act: -0.1700
Data Index: 8236606 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8535. Min Range: -4.8535
Max Act: 4.6660. Min Act: -0.1700
Data Index: 2395517 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8535. Min Range: -4.8535
Max Act: 4.6660. Min Act: -0.1700
Data Index: 8813652 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8535. Min Range: -4.8535
Max Act: 4.6660. Min Act: -0.1700
Data Index: 1866926 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8535. Min Range: -4.8535
Max Act: 4.6660. Min Act: -0.1700
Data Index: 7355136 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8535. Min Range: -4.8535
Max Act: 4.6347. Min Act: -0.1700
Data Index: 3506906 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8535. Min Range: -4.8535
Max Act: 4.6035. Min Act: -0.1700
Data Index: 8430674 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8535. Min Range: -4.8535
Max Act: 4.6035. Min Act: -0.1700
Data Index: 4631183 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8535. Min Range: -4.8535
Max Act: 4.6035. Min Act: -0.1700
Data Index: 7245985 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8535. Min Range: -4.8535
Max Act: 4.5722. Min Act: -0.1700
Data Index: 4130038 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8535. Min Range: -4.8535
Max Act: 4.6035. Min Act: -0.1700
Data Index: 3639415 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8535. Min Range: -4.8535
Max Act: 4.6035. Min Act: -0.1700
Data Index: 3459005 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8535. Min Range: -4.8535
Max Act: 4.6035. Min Act: -0.1700
Data Index: 8321775 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8535. Min Range: -4.8535
Max Act: 4.6035. Min Act: -0.1700
Data Index: 8084479 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8535. Min Range: -4.8535
Max Act: 4.6035. Min Act: -0.1700
Data Index: 1357930 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8535. Min Range: -4.8535
Max Act: 4.5722. Min Act: -0.1700
Data Index: 3044812 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #19