Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5528 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1784. Min Range: -7.1784
Max Act: 7.1784. Min Act: -0.1700
Data Index: 8801556 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1784. Min Range: -7.1784
Max Act: 7.1471. Min Act: -0.1700
Data Index: 1262130 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1784. Min Range: -7.1784
Max Act: 7.1471. Min Act: -0.1700
Data Index: 962223 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1784. Min Range: -7.1784
Max Act: 7.0534. Min Act: -0.1700
Data Index: 3623898 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1784. Min Range: -7.1784
Max Act: 6.9909. Min Act: -0.1700
Data Index: 315518 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1784. Min Range: -7.1784
Max Act: 6.9284. Min Act: -0.1700
Data Index: 3531802 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1784. Min Range: -7.1784
Max Act: 6.8971. Min Act: -0.1700
Data Index: 1788167 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1784. Min Range: -7.1784
Max Act: 6.8346. Min Act: -0.1700
Data Index: 7990095 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1784. Min Range: -7.1784
Max Act: 6.8346. Min Act: -0.1700
Data Index: 5526246 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1784. Min Range: -7.1784
Max Act: 6.8346. Min Act: -0.1700
Data Index: 5376182 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1784. Min Range: -7.1784
Max Act: 6.8034. Min Act: -0.1700
Data Index: 1398717 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1784. Min Range: -7.1784
Max Act: 6.8034. Min Act: -0.1700
Data Index: 8226426 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1784. Min Range: -7.1784
Max Act: 6.8034. Min Act: -0.1700
Data Index: 4663076 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1784. Min Range: -7.1784
Max Act: 6.7721. Min Act: -0.1700
Data Index: 6854389 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1784. Min Range: -7.1784
Max Act: 6.7721. Min Act: -0.1700
Data Index: 985070 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1784. Min Range: -7.1784
Max Act: 6.7721. Min Act: -0.1700
Data Index: 7139013 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1784. Min Range: -7.1784
Max Act: 6.7721. Min Act: -0.1700
Data Index: 4339062 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1784. Min Range: -7.1784
Max Act: 6.7409. Min Act: -0.1700
Data Index: 3014295 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1784. Min Range: -7.1784
Max Act: 6.7409. Min Act: -0.1700
Data Index: 6617291 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1784. Min Range: -7.1784
Max Act: 6.7409. Min Act: -0.1700
Data Index: 8795775 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #19