Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4078 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2330. Min Range: -5.2330
Max Act: 5.2330. Min Act: -0.1700
Data Index: 6767211 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2330. Min Range: -5.2330
Max Act: 5.2330. Min Act: -0.1700
Data Index: 57822 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2330. Min Range: -5.2330
Max Act: 5.1080. Min Act: -0.1700
Data Index: 1918754 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2330. Min Range: -5.2330
Max Act: 5.0142. Min Act: -0.1700
Data Index: 7617576 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2330. Min Range: -5.2330
Max Act: 5.0142. Min Act: -0.1700
Data Index: 909334 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2330. Min Range: -5.2330
Max Act: 5.0142. Min Act: -0.1700
Data Index: 5319964 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2330. Min Range: -5.2330
Max Act: 4.9830. Min Act: -0.1700
Data Index: 3789802 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2330. Min Range: -5.2330
Max Act: 4.9830. Min Act: -0.1700
Data Index: 7862265 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2330. Min Range: -5.2330
Max Act: 4.9517. Min Act: -0.1700
Data Index: 6280659 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2330. Min Range: -5.2330
Max Act: 4.9205. Min Act: -0.1700
Data Index: 2926507 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2330. Min Range: -5.2330
Max Act: 4.9205. Min Act: -0.1700
Data Index: 3046804 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2330. Min Range: -5.2330
Max Act: 4.8892. Min Act: -0.1700
Data Index: 1975021 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2330. Min Range: -5.2330
Max Act: 4.8580. Min Act: -0.1700
Data Index: 3907767 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2330. Min Range: -5.2330
Max Act: 4.8580. Min Act: -0.1700
Data Index: 7900176 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2330. Min Range: -5.2330
Max Act: 4.8580. Min Act: -0.1700
Data Index: 44705 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2330. Min Range: -5.2330
Max Act: 4.8267. Min Act: -0.1700
Data Index: 4495458 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2330. Min Range: -5.2330
Max Act: 4.8892. Min Act: -0.1700
Data Index: 740731 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2330. Min Range: -5.2330
Max Act: 4.8580. Min Act: -0.1700
Data Index: 41696 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2330. Min Range: -5.2330
Max Act: 4.8267. Min Act: -0.1700
Data Index: 7149244 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2330. Min Range: -5.2330
Max Act: 4.8267. Min Act: -0.1700
Data Index: 5983035 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #19