Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 614 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6418. Min Range: -4.6418
Max Act: 4.6418. Min Act: -0.1700
Data Index: 3352045 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6418. Min Range: -4.6418
Max Act: 4.6105. Min Act: -0.1700
Data Index: 6463257 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6418. Min Range: -4.6418
Max Act: 4.6105. Min Act: -0.1700
Data Index: 367149 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6418. Min Range: -4.6418
Max Act: 4.5480. Min Act: -0.1700
Data Index: 883154 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6418. Min Range: -4.6418
Max Act: 4.4230. Min Act: -0.1700
Data Index: 8302544 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6418. Min Range: -4.6418
Max Act: 4.3918. Min Act: -0.1700
Data Index: 1198590 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6418. Min Range: -4.6418
Max Act: 4.3605. Min Act: -0.1700
Data Index: 3152075 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6418. Min Range: -4.6418
Max Act: 4.3918. Min Act: -0.1700
Data Index: 6782744 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6418. Min Range: -4.6418
Max Act: 4.3605. Min Act: -0.1700
Data Index: 2635810 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6418. Min Range: -4.6418
Max Act: 4.3293. Min Act: -0.1700
Data Index: 8214342 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6418. Min Range: -4.6418
Max Act: 4.3293. Min Act: -0.1700
Data Index: 2947203 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6418. Min Range: -4.6418
Max Act: 4.3293. Min Act: -0.1700
Data Index: 527108 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6418. Min Range: -4.6418
Max Act: 4.3293. Min Act: -0.1700
Data Index: 6260716 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6418. Min Range: -4.6418
Max Act: 4.3293. Min Act: -0.1700
Data Index: 666660 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6418. Min Range: -4.6418
Max Act: 4.3293. Min Act: -0.1700
Data Index: 2553142 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6418. Min Range: -4.6418
Max Act: 4.2980. Min Act: -0.1700
Data Index: 3981084 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6418. Min Range: -4.6418
Max Act: 4.2980. Min Act: -0.1700
Data Index: 4016046 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6418. Min Range: -4.6418
Max Act: 4.3293. Min Act: -0.1700
Data Index: 48203 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6418. Min Range: -4.6418
Max Act: 4.2667. Min Act: -0.1700
Data Index: 7080395 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6418. Min Range: -4.6418
Max Act: 4.2667. Min Act: -0.1700
Data Index: 4876338 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #19