Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2814 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1608. Min Range: -7.1608
Max Act: 7.1608. Min Act: -0.1700
Data Index: 4692334 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1608. Min Range: -7.1608
Max Act: 7.0983. Min Act: -0.1700
Data Index: 7188882 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1608. Min Range: -7.1608
Max Act: 7.0983. Min Act: -0.1700
Data Index: 3407124 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1608. Min Range: -7.1608
Max Act: 7.0983. Min Act: -0.1700
Data Index: 8344998 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1608. Min Range: -7.1608
Max Act: 7.0358. Min Act: -0.1700
Data Index: 8404242 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1608. Min Range: -7.1608
Max Act: 7.0045. Min Act: -0.1700
Data Index: 4701824 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1608. Min Range: -7.1608
Max Act: 6.9733. Min Act: -0.1700
Data Index: 4821270 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1608. Min Range: -7.1608
Max Act: 6.9733. Min Act: -0.1700
Data Index: 1641325 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1608. Min Range: -7.1608
Max Act: 6.9108. Min Act: -0.1700
Data Index: 3687705 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1608. Min Range: -7.1608
Max Act: 6.8795. Min Act: -0.1700
Data Index: 162973 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1608. Min Range: -7.1608
Max Act: 6.8795. Min Act: -0.1700
Data Index: 8455846 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1608. Min Range: -7.1608
Max Act: 6.8170. Min Act: -0.1700
Data Index: 5744728 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1608. Min Range: -7.1608
Max Act: 6.8170. Min Act: -0.1700
Data Index: 1368990 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1608. Min Range: -7.1608
Max Act: 6.8170. Min Act: -0.1700
Data Index: 2720951 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1608. Min Range: -7.1608
Max Act: 6.7858. Min Act: -0.1700
Data Index: 1590266 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1608. Min Range: -7.1608
Max Act: 6.7858. Min Act: -0.1700
Data Index: 3906619 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1608. Min Range: -7.1608
Max Act: 6.7858. Min Act: -0.1700
Data Index: 5276232 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1608. Min Range: -7.1608
Max Act: 6.7858. Min Act: -0.1700
Data Index: 6100466 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1608. Min Range: -7.1608
Max Act: 6.7545. Min Act: -0.1700
Data Index: 5643483 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1608. Min Range: -7.1608
Max Act: 6.7233. Min Act: -0.1700
Data Index: 2021589 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #19