Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2284 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3637. Min Range: -7.3637
Max Act: 7.3637. Min Act: -0.1700
Data Index: 8005280 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3637. Min Range: -7.3637
Max Act: 7.3324. Min Act: -0.1700
Data Index: 7397236 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3637. Min Range: -7.3637
Max Act: 7.3324. Min Act: -0.1700
Data Index: 1431320 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3637. Min Range: -7.3637
Max Act: 7.1762. Min Act: -0.1700
Data Index: 4270788 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3637. Min Range: -7.3637
Max Act: 7.1449. Min Act: -0.1700
Data Index: 6036196 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3637. Min Range: -7.3637
Max Act: 7.1137. Min Act: -0.1700
Data Index: 8769853 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3637. Min Range: -7.3637
Max Act: 7.0824. Min Act: -0.1700
Data Index: 6053462 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3637. Min Range: -7.3637
Max Act: 7.0824. Min Act: -0.1700
Data Index: 8641302 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3637. Min Range: -7.3637
Max Act: 7.0512. Min Act: -0.1700
Data Index: 8685654 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3637. Min Range: -7.3637
Max Act: 7.0512. Min Act: -0.1700
Data Index: 3993459 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3637. Min Range: -7.3637
Max Act: 7.0199. Min Act: -0.1700
Data Index: 5065425 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3637. Min Range: -7.3637
Max Act: 7.0199. Min Act: -0.1700
Data Index: 3077372 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3637. Min Range: -7.3637
Max Act: 7.0199. Min Act: -0.1700
Data Index: 6875603 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3637. Min Range: -7.3637
Max Act: 7.0199. Min Act: -0.1700
Data Index: 546056 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3637. Min Range: -7.3637
Max Act: 6.9574. Min Act: -0.1700
Data Index: 2678530 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3637. Min Range: -7.3637
Max Act: 6.9574. Min Act: -0.1700
Data Index: 7610594 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3637. Min Range: -7.3637
Max Act: 6.9262. Min Act: -0.1700
Data Index: 1789587 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3637. Min Range: -7.3637
Max Act: 6.8949. Min Act: -0.1700
Data Index: 1533058 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3637. Min Range: -7.3637
Max Act: 6.8637. Min Act: -0.1700
Data Index: 8808953 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3637. Min Range: -7.3637
Max Act: 6.8324. Min Act: -0.1700
Data Index: 3515357 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #19