Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2943 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4179. Min Range: -6.4179
Max Act: 6.4179. Min Act: -0.1700
Data Index: 5479911 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4179. Min Range: -6.4179
Max Act: 6.3241. Min Act: -0.1700
Data Index: 6796073 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4179. Min Range: -6.4179
Max Act: 6.1991. Min Act: -0.1700
Data Index: 5469461 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4179. Min Range: -6.4179
Max Act: 6.1366. Min Act: -0.1700
Data Index: 695896 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4179. Min Range: -6.4179
Max Act: 6.0741. Min Act: -0.1700
Data Index: 6414606 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4179. Min Range: -6.4179
Max Act: 6.0116. Min Act: -0.1700
Data Index: 8646898 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4179. Min Range: -6.4179
Max Act: 6.0116. Min Act: -0.1700
Data Index: 870481 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4179. Min Range: -6.4179
Max Act: 6.0429. Min Act: -0.1700
Data Index: 7357851 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4179. Min Range: -6.4179
Max Act: 5.9804. Min Act: -0.1700
Data Index: 4378627 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4179. Min Range: -6.4179
Max Act: 6.0116. Min Act: -0.1700
Data Index: 8668159 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4179. Min Range: -6.4179
Max Act: 5.9179. Min Act: -0.1700
Data Index: 8163658 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4179. Min Range: -6.4179
Max Act: 5.9491. Min Act: -0.1700
Data Index: 5810169 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4179. Min Range: -6.4179
Max Act: 5.9491. Min Act: -0.1700
Data Index: 2830411 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4179. Min Range: -6.4179
Max Act: 5.9491. Min Act: -0.1700
Data Index: 2429777 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4179. Min Range: -6.4179
Max Act: 5.8866. Min Act: -0.1700
Data Index: 2215892 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4179. Min Range: -6.4179
Max Act: 5.9179. Min Act: -0.1700
Data Index: 554386 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4179. Min Range: -6.4179
Max Act: 5.8866. Min Act: -0.1700
Data Index: 5382761 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4179. Min Range: -6.4179
Max Act: 5.8866. Min Act: -0.1700
Data Index: 1170509 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4179. Min Range: -6.4179
Max Act: 5.8866. Min Act: -0.1700
Data Index: 1288899 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4179. Min Range: -6.4179
Max Act: 5.8866. Min Act: -0.1700
Data Index: 3806859 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #19