Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4001 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2127. Min Range: -3.2127
Max Act: 3.2127. Min Act: -0.1700
Data Index: 4630193 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2127. Min Range: -3.2127
Max Act: 3.0078. Min Act: -0.1700
Data Index: 194157 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2127. Min Range: -3.2127
Max Act: 2.9920. Min Act: -0.1700
Data Index: 1557749 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2127. Min Range: -3.2127
Max Act: 2.9129. Min Act: -0.1700
Data Index: 8629095 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2127. Min Range: -3.2127
Max Act: 2.8970. Min Act: -0.1700
Data Index: 2458955 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2127. Min Range: -3.2127
Max Act: 2.8812. Min Act: -0.1700
Data Index: 1357116 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2127. Min Range: -3.2127
Max Act: 2.8812. Min Act: -0.1700
Data Index: 2341012 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2127. Min Range: -3.2127
Max Act: 2.8812. Min Act: -0.1700
Data Index: 2882669 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2127. Min Range: -3.2127
Max Act: 2.8653. Min Act: -0.1700
Data Index: 5983264 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2127. Min Range: -3.2127
Max Act: 2.8653. Min Act: -0.1700
Data Index: 4043450 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2127. Min Range: -3.2127
Max Act: 2.8812. Min Act: -0.1700
Data Index: 4076991 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2127. Min Range: -3.2127
Max Act: 2.8494. Min Act: -0.1700
Data Index: 3126775 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2127. Min Range: -3.2127
Max Act: 2.8653. Min Act: -0.1700
Data Index: 6900896 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2127. Min Range: -3.2127
Max Act: 2.8494. Min Act: -0.1700
Data Index: 980621 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2127. Min Range: -3.2127
Max Act: 2.8494. Min Act: -0.1700
Data Index: 6951959 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2127. Min Range: -3.2127
Max Act: 2.8335. Min Act: -0.1700
Data Index: 6661854 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2127. Min Range: -3.2127
Max Act: 2.8335. Min Act: -0.1700
Data Index: 6333235 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2127. Min Range: -3.2127
Max Act: 2.8335. Min Act: -0.1700
Data Index: 1650423 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2127. Min Range: -3.2127
Max Act: 2.8176. Min Act: -0.1700
Data Index: 246255 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2127. Min Range: -3.2127
Max Act: 2.8176. Min Act: -0.1700
Data Index: 6488113 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #19