Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1111 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6545. Min Range: -3.6545
Max Act: 3.6545. Min Act: -0.1700
Data Index: 3897903 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6545. Min Range: -3.6545
Max Act: 3.6545. Min Act: -0.1700
Data Index: 6472217 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6545. Min Range: -3.6545
Max Act: 3.6545. Min Act: -0.1700
Data Index: 850047 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6545. Min Range: -3.6545
Max Act: 3.6388. Min Act: -0.1700
Data Index: 5296794 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6545. Min Range: -3.6545
Max Act: 3.5605. Min Act: -0.1700
Data Index: 3657036 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6545. Min Range: -3.6545
Max Act: 3.5605. Min Act: -0.1700
Data Index: 5430397 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6545. Min Range: -3.6545
Max Act: 3.4979. Min Act: -0.1700
Data Index: 2242631 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6545. Min Range: -3.6545
Max Act: 3.4979. Min Act: -0.1700
Data Index: 755220 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6545. Min Range: -3.6545
Max Act: 3.4822. Min Act: -0.1700
Data Index: 3064748 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6545. Min Range: -3.6545
Max Act: 3.4822. Min Act: -0.1700
Data Index: 4979747 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6545. Min Range: -3.6545
Max Act: 3.4666. Min Act: -0.1700
Data Index: 5549848 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6545. Min Range: -3.6545
Max Act: 3.4352. Min Act: -0.1700
Data Index: 7148892 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6545. Min Range: -3.6545
Max Act: 3.4196. Min Act: -0.1700
Data Index: 6910689 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6545. Min Range: -3.6545
Max Act: 3.4196. Min Act: -0.1700
Data Index: 5877292 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6545. Min Range: -3.6545
Max Act: 3.4039. Min Act: -0.1700
Data Index: 7372725 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6545. Min Range: -3.6545
Max Act: 3.4039. Min Act: -0.1700
Data Index: 3671386 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6545. Min Range: -3.6545
Max Act: 3.4039. Min Act: -0.1700
Data Index: 8448698 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6545. Min Range: -3.6545
Max Act: 3.3882. Min Act: -0.1700
Data Index: 2114654 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6545. Min Range: -3.6545
Max Act: 3.4039. Min Act: -0.1700
Data Index: 1939283 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6545. Min Range: -3.6545
Max Act: 3.3882. Min Act: -0.1700
Data Index: 6080386 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #19