Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3403 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4711. Min Range: -9.4711
Max Act: 9.4711. Min Act: -0.1700
Data Index: 8563751 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4711. Min Range: -9.4711
Max Act: 9.3461. Min Act: -0.1700
Data Index: 1085526 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4711. Min Range: -9.4711
Max Act: 9.3461. Min Act: -0.1700
Data Index: 6975303 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4711. Min Range: -9.4711
Max Act: 9.2836. Min Act: -0.1700
Data Index: 150470 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4711. Min Range: -9.4711
Max Act: 9.2211. Min Act: -0.1700
Data Index: 8434316 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4711. Min Range: -9.4711
Max Act: 9.2211. Min Act: -0.1700
Data Index: 7474212 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4711. Min Range: -9.4711
Max Act: 9.0961. Min Act: -0.1700
Data Index: 4197288 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4711. Min Range: -9.4711
Max Act: 9.0336. Min Act: -0.1700
Data Index: 1395842 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4711. Min Range: -9.4711
Max Act: 8.9086. Min Act: -0.1700
Data Index: 5467279 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4711. Min Range: -9.4711
Max Act: 8.9711. Min Act: -0.1700
Data Index: 2577633 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4711. Min Range: -9.4711
Max Act: 8.9711. Min Act: -0.1693
Data Index: 4892649 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4711. Min Range: -9.4711
Max Act: 8.9086. Min Act: -0.1700
Data Index: 6088532 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4711. Min Range: -9.4711
Max Act: 8.9086. Min Act: -0.1700
Data Index: 7420365 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4711. Min Range: -9.4711
Max Act: 8.8461. Min Act: -0.1700
Data Index: 8792825 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4711. Min Range: -9.4711
Max Act: 8.8461. Min Act: -0.1700
Data Index: 6651081 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4711. Min Range: -9.4711
Max Act: 8.8461. Min Act: -0.1700
Data Index: 3153408 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4711. Min Range: -9.4711
Max Act: 8.8461. Min Act: -0.1700
Data Index: 5620010 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4711. Min Range: -9.4711
Max Act: 8.7836. Min Act: -0.1700
Data Index: 972083 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4711. Min Range: -9.4711
Max Act: 8.7836. Min Act: -0.1700
Data Index: 1226052 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4711. Min Range: -9.4711
Max Act: 8.7836. Min Act: -0.1700
Data Index: 3375741 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #19