Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 898 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3101. Min Range: -7.3101
Max Act: 7.3101. Min Act: -0.1700
Data Index: 5646952 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3101. Min Range: -7.3101
Max Act: 7.2788. Min Act: -0.1700
Data Index: 1231554 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3101. Min Range: -7.3101
Max Act: 7.1851. Min Act: -0.1700
Data Index: 4807532 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3101. Min Range: -7.3101
Max Act: 7.1538. Min Act: -0.1700
Data Index: 4387224 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3101. Min Range: -7.3101
Max Act: 7.0601. Min Act: -0.1700
Data Index: 5212526 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3101. Min Range: -7.3101
Max Act: 7.0601. Min Act: -0.1700
Data Index: 7231867 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3101. Min Range: -7.3101
Max Act: 7.0601. Min Act: -0.1700
Data Index: 3690309 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3101. Min Range: -7.3101
Max Act: 7.0288. Min Act: -0.1700
Data Index: 114835 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3101. Min Range: -7.3101
Max Act: 7.0288. Min Act: -0.1700
Data Index: 6206966 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3101. Min Range: -7.3101
Max Act: 6.9663. Min Act: -0.1700
Data Index: 6557817 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3101. Min Range: -7.3101
Max Act: 6.9351. Min Act: -0.1700
Data Index: 8135007 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3101. Min Range: -7.3101
Max Act: 6.9663. Min Act: -0.1700
Data Index: 7439480 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3101. Min Range: -7.3101
Max Act: 6.9351. Min Act: -0.1700
Data Index: 5727376 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3101. Min Range: -7.3101
Max Act: 6.9038. Min Act: -0.1700
Data Index: 8077067 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3101. Min Range: -7.3101
Max Act: 6.9038. Min Act: -0.1700
Data Index: 6164268 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3101. Min Range: -7.3101
Max Act: 6.8726. Min Act: -0.1700
Data Index: 1314434 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3101. Min Range: -7.3101
Max Act: 6.8413. Min Act: -0.1700
Data Index: 5229911 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3101. Min Range: -7.3101
Max Act: 6.8413. Min Act: -0.1700
Data Index: 4807533 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3101. Min Range: -7.3101
Max Act: 6.7476. Min Act: -0.1700
Data Index: 819785 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3101. Min Range: -7.3101
Max Act: 6.7788. Min Act: -0.1700
Data Index: 4459308 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #19