Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3841 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4743. Min Range: -5.4743
Max Act: 5.4743. Min Act: -0.1700
Data Index: 659825 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4743. Min Range: -5.4743
Max Act: 5.2555. Min Act: -0.1700
Data Index: 5138708 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4743. Min Range: -5.4743
Max Act: 5.1618. Min Act: -0.1700
Data Index: 1261257 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4743. Min Range: -5.4743
Max Act: 5.0993. Min Act: -0.1700
Data Index: 1082333 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4743. Min Range: -5.4743
Max Act: 5.0993. Min Act: -0.1700
Data Index: 1687301 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4743. Min Range: -5.4743
Max Act: 5.0680. Min Act: -0.1700
Data Index: 6167741 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4743. Min Range: -5.4743
Max Act: 5.0680. Min Act: -0.1700
Data Index: 3730847 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4743. Min Range: -5.4743
Max Act: 4.9743. Min Act: -0.1700
Data Index: 2788955 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4743. Min Range: -5.4743
Max Act: 4.9118. Min Act: -0.1700
Data Index: 183737 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4743. Min Range: -5.4743
Max Act: 4.8805. Min Act: -0.1700
Data Index: 8804346 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4743. Min Range: -5.4743
Max Act: 4.8805. Min Act: -0.1700
Data Index: 7942105 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4743. Min Range: -5.4743
Max Act: 4.8493. Min Act: -0.1700
Data Index: 8787452 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4743. Min Range: -5.4743
Max Act: 4.8493. Min Act: -0.1700
Data Index: 3447799 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4743. Min Range: -5.4743
Max Act: 4.8493. Min Act: -0.1700
Data Index: 5202131 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4743. Min Range: -5.4743
Max Act: 4.8493. Min Act: -0.1700
Data Index: 7158340 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4743. Min Range: -5.4743
Max Act: 4.7868. Min Act: -0.1700
Data Index: 726640 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4743. Min Range: -5.4743
Max Act: 4.7868. Min Act: -0.1700
Data Index: 8067633 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4743. Min Range: -5.4743
Max Act: 4.7868. Min Act: -0.1700
Data Index: 3830258 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4743. Min Range: -5.4743
Max Act: 4.7868. Min Act: -0.1700
Data Index: 1995003 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4743. Min Range: -5.4743
Max Act: 4.7555. Min Act: -0.1700
Data Index: 4970667 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #19