Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 28 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1518. Min Range: -5.1518
Max Act: 5.1518. Min Act: -0.1700
Data Index: 6218012 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1518. Min Range: -5.1518
Max Act: 4.9956. Min Act: -0.1700
Data Index: 3482030 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1518. Min Range: -5.1518
Max Act: 4.9331. Min Act: -0.1700
Data Index: 5272411 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1518. Min Range: -5.1518
Max Act: 4.9331. Min Act: -0.1700
Data Index: 208729 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1518. Min Range: -5.1518
Max Act: 4.9956. Min Act: -0.1700
Data Index: 652357 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1518. Min Range: -5.1518
Max Act: 4.9331. Min Act: -0.1700
Data Index: 5067116 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1518. Min Range: -5.1518
Max Act: 4.8706. Min Act: -0.1700
Data Index: 8312365 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1518. Min Range: -5.1518
Max Act: 4.8706. Min Act: -0.1700
Data Index: 1390850 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1518. Min Range: -5.1518
Max Act: 4.8393. Min Act: -0.1700
Data Index: 1988538 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1518. Min Range: -5.1518
Max Act: 4.8081. Min Act: -0.1700
Data Index: 659906 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1518. Min Range: -5.1518
Max Act: 4.8393. Min Act: -0.1700
Data Index: 6236872 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1518. Min Range: -5.1518
Max Act: 4.7768. Min Act: -0.1700
Data Index: 8656927 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1518. Min Range: -5.1518
Max Act: 4.7456. Min Act: -0.1700
Data Index: 1390844 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1518. Min Range: -5.1518
Max Act: 4.7456. Min Act: -0.1700
Data Index: 3360277 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1518. Min Range: -5.1518
Max Act: 4.7456. Min Act: -0.1700
Data Index: 3698186 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1518. Min Range: -5.1518
Max Act: 4.7456. Min Act: -0.1700
Data Index: 4182447 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1518. Min Range: -5.1518
Max Act: 4.7456. Min Act: -0.1700
Data Index: 3594368 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1518. Min Range: -5.1518
Max Act: 4.7456. Min Act: -0.1700
Data Index: 6350828 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1518. Min Range: -5.1518
Max Act: 4.7143. Min Act: -0.1700
Data Index: 8533074 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1518. Min Range: -5.1518
Max Act: 4.7143. Min Act: -0.1700
Data Index: 1069088 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #19