Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1540 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9479. Min Range: -2.9479
Max Act: 2.9479. Min Act: -0.1700
Data Index: 5577130 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9479. Min Range: -2.9479
Max Act: 2.8369. Min Act: -0.1700
Data Index: 8739876 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9479. Min Range: -2.9479
Max Act: 2.8051. Min Act: -0.1700
Data Index: 4754155 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9479. Min Range: -2.9479
Max Act: 2.7891. Min Act: -0.1700
Data Index: 7833612 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9479. Min Range: -2.9479
Max Act: 2.7572. Min Act: -0.1700
Data Index: 4500986 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9479. Min Range: -2.9479
Max Act: 2.7413. Min Act: -0.1700
Data Index: 6633707 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9479. Min Range: -2.9479
Max Act: 2.7093. Min Act: -0.1700
Data Index: 7202137 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9479. Min Range: -2.9479
Max Act: 2.6933. Min Act: -0.1700
Data Index: 7334242 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9479. Min Range: -2.9479
Max Act: 2.6933. Min Act: -0.1700
Data Index: 2707818 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9479. Min Range: -2.9479
Max Act: 2.6613. Min Act: -0.1700
Data Index: 5929616 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9479. Min Range: -2.9479
Max Act: 2.6613. Min Act: -0.1700
Data Index: 6694118 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9479. Min Range: -2.9479
Max Act: 2.6452. Min Act: -0.1700
Data Index: 326768 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9479. Min Range: -2.9479
Max Act: 2.6292. Min Act: -0.1700
Data Index: 3837244 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9479. Min Range: -2.9479
Max Act: 2.6131. Min Act: -0.1699
Data Index: 3461300 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9479. Min Range: -2.9479
Max Act: 2.6131. Min Act: -0.1700
Data Index: 8186399 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9479. Min Range: -2.9479
Max Act: 2.5970. Min Act: -0.1700
Data Index: 6021529 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9479. Min Range: -2.9479
Max Act: 2.5970. Min Act: -0.1700
Data Index: 5386869 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9479. Min Range: -2.9479
Max Act: 2.6131. Min Act: -0.1700
Data Index: 5781097 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9479. Min Range: -2.9479
Max Act: 2.5809. Min Act: -0.1700
Data Index: 3584394 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9479. Min Range: -2.9479
Max Act: 2.5809. Min Act: -0.1700
Data Index: 7441429 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #19