Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3120 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.3405. Min Act: -0.1700
Data Index: 3198428 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.3405. Min Act: -0.1700
Data Index: 7721936 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.3092. Min Act: -0.1700
Data Index: 4331653 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.2780. Min Act: -0.1700
Data Index: 2304247 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.2467. Min Act: -0.1700
Data Index: 3991983 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.2155. Min Act: -0.1700
Data Index: 3721474 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.1842. Min Act: -0.1700
Data Index: 7469982 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.1529. Min Act: -0.1700
Data Index: 7375392 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.1529. Min Act: -0.1700
Data Index: 1540696 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.1217. Min Act: -0.1700
Data Index: 873999 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.1217. Min Act: -0.1700
Data Index: 3313095 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.1217. Min Act: -0.1700
Data Index: 7770653 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.0904. Min Act: -0.1700
Data Index: 8807670 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.1217. Min Act: -0.1700
Data Index: 6205478 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.1217. Min Act: -0.1700
Data Index: 2980059 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.1217. Min Act: -0.1700
Data Index: 2037495 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.1217. Min Act: -0.1700
Data Index: 5541568 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.0904. Min Act: -0.1700
Data Index: 3894490 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.0904. Min Act: -0.1700
Data Index: 2513423 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.0592. Min Act: -0.1700
Data Index: 1546604 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #19