Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4977 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1946. Min Range: -6.1946
Max Act: 6.1946. Min Act: -0.1700
Data Index: 7320135 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1946. Min Range: -6.1946
Max Act: 6.1321. Min Act: -0.1700
Data Index: 4033342 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1946. Min Range: -6.1946
Max Act: 6.1009. Min Act: -0.1700
Data Index: 6289625 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1946. Min Range: -6.1946
Max Act: 6.0384. Min Act: -0.1700
Data Index: 5575502 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1946. Min Range: -6.1946
Max Act: 5.9446. Min Act: -0.1700
Data Index: 5678112 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1946. Min Range: -6.1946
Max Act: 5.9446. Min Act: -0.1700
Data Index: 3480883 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1946. Min Range: -6.1946
Max Act: 5.9134. Min Act: -0.1700
Data Index: 7599476 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1946. Min Range: -6.1946
Max Act: 5.9134. Min Act: -0.1700
Data Index: 3798162 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1946. Min Range: -6.1946
Max Act: 5.8821. Min Act: -0.1700
Data Index: 7599472 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1946. Min Range: -6.1946
Max Act: 5.8821. Min Act: -0.1700
Data Index: 8116873 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1946. Min Range: -6.1946
Max Act: 5.8509. Min Act: -0.1700
Data Index: 2436272 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1946. Min Range: -6.1946
Max Act: 5.9134. Min Act: -0.1700
Data Index: 1738211 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1946. Min Range: -6.1946
Max Act: 5.8509. Min Act: -0.1700
Data Index: 5296004 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1946. Min Range: -6.1946
Max Act: 5.8509. Min Act: -0.1700
Data Index: 7294077 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1946. Min Range: -6.1946
Max Act: 5.8509. Min Act: -0.1700
Data Index: 3731243 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1946. Min Range: -6.1946
Max Act: 5.8509. Min Act: -0.1700
Data Index: 8803090 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1946. Min Range: -6.1946
Max Act: 5.8509. Min Act: -0.1700
Data Index: 592808 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1946. Min Range: -6.1946
Max Act: 5.8509. Min Act: -0.1700
Data Index: 8116872 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1946. Min Range: -6.1946
Max Act: 5.8509. Min Act: -0.1700
Data Index: 4898943 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1946. Min Range: -6.1946
Max Act: 5.8196. Min Act: -0.1700
Data Index: 3480882 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #19