Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3433 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.8995. Min Range: -0.8995
Max Act: 0.8995. Min Act: -0.1700
Data Index: 8299394 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.8995. Min Range: -0.8995
Max Act: 0.8739. Min Act: -0.1698
Data Index: 1854141 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.8995. Min Range: -0.8995
Max Act: 0.8654. Min Act: -0.1700
Data Index: 1939825 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.8995. Min Range: -0.8995
Max Act: 0.8739. Min Act: -0.1699
Data Index: 5026022 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.8995. Min Range: -0.8995
Max Act: 0.8654. Min Act: -0.1700
Data Index: 5618818 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.8995. Min Range: -0.8995
Max Act: 0.8569. Min Act: -0.1700
Data Index: 863409 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.8995. Min Range: -0.8995
Max Act: 0.8315. Min Act: -0.1700
Data Index: 4964955 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.8995. Min Range: -0.8995
Max Act: 0.8315. Min Act: -0.1684
Data Index: 5928029 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.8995. Min Range: -0.8995
Max Act: 0.8231. Min Act: -0.1700
Data Index: 1915089 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.8995. Min Range: -0.8995
Max Act: 0.8231. Min Act: -0.1607
Data Index: 7383325 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.8995. Min Range: -0.8995
Max Act: 0.8231. Min Act: -0.1691
Data Index: 456896 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.8995. Min Range: -0.8995
Max Act: 0.8147. Min Act: -0.1700
Data Index: 7570462 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.8995. Min Range: -0.8995
Max Act: 0.8062. Min Act: -0.1700
Data Index: 5662177 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.8995. Min Range: -0.8995
Max Act: 0.8147. Min Act: -0.1638
Data Index: 7829215 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.8995. Min Range: -0.8995
Max Act: 0.8062. Min Act: -0.1658
Data Index: 1996394 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.8995. Min Range: -0.8995
Max Act: 0.8062. Min Act: -0.1700
Data Index: 8401934 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.8995. Min Range: -0.8995
Max Act: 0.8062. Min Act: -0.1700
Data Index: 4990659 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.8995. Min Range: -0.8995
Max Act: 0.8062. Min Act: -0.1685
Data Index: 3113827 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.8995. Min Range: -0.8995
Max Act: 0.8147. Min Act: -0.1654
Data Index: 7123162 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.8995. Min Range: -0.8995
Max Act: 0.7979. Min Act: -0.1687
Data Index: 7514523 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #19