Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4974 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4308. Min Range: -5.4308
Max Act: 5.4308. Min Act: -0.1700
Data Index: 8257998 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4308. Min Range: -5.4308
Max Act: 5.4308. Min Act: -0.1700
Data Index: 6466935 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4308. Min Range: -5.4308
Max Act: 5.4308. Min Act: -0.1700
Data Index: 3684567 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4308. Min Range: -5.4308
Max Act: 5.2746. Min Act: -0.1700
Data Index: 5734864 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4308. Min Range: -5.4308
Max Act: 5.2746. Min Act: -0.1700
Data Index: 1151956 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4308. Min Range: -5.4308
Max Act: 5.2746. Min Act: -0.1700
Data Index: 5689116 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4308. Min Range: -5.4308
Max Act: 5.2433. Min Act: -0.1700
Data Index: 4883755 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4308. Min Range: -5.4308
Max Act: 5.2433. Min Act: -0.1700
Data Index: 4189671 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4308. Min Range: -5.4308
Max Act: 5.2121. Min Act: -0.1700
Data Index: 1367445 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4308. Min Range: -5.4308
Max Act: 5.1808. Min Act: -0.1700
Data Index: 2601529 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4308. Min Range: -5.4308
Max Act: 5.1808. Min Act: -0.1700
Data Index: 4232021 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4308. Min Range: -5.4308
Max Act: 5.1808. Min Act: -0.1700
Data Index: 3063956 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4308. Min Range: -5.4308
Max Act: 5.1808. Min Act: -0.1700
Data Index: 3534246 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4308. Min Range: -5.4308
Max Act: 5.1496. Min Act: -0.1700
Data Index: 1309170 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4308. Min Range: -5.4308
Max Act: 5.1496. Min Act: -0.1700
Data Index: 7654812 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4308. Min Range: -5.4308
Max Act: 5.1496. Min Act: -0.1700
Data Index: 1104317 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4308. Min Range: -5.4308
Max Act: 5.1496. Min Act: -0.1700
Data Index: 8432448 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4308. Min Range: -5.4308
Max Act: 5.1183. Min Act: -0.1700
Data Index: 63390 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4308. Min Range: -5.4308
Max Act: 5.1183. Min Act: -0.1700
Data Index: 7189329 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4308. Min Range: -5.4308
Max Act: 5.1183. Min Act: -0.1700
Data Index: 6118358 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #19