Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3520 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2438. Min Range: -4.2438
Max Act: 4.2438. Min Act: -0.1700
Data Index: 3399631 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2438. Min Range: -4.2438
Max Act: 4.1188. Min Act: -0.1700
Data Index: 3814023 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2438. Min Range: -4.2438
Max Act: 4.1188. Min Act: -0.1700
Data Index: 661430 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2438. Min Range: -4.2438
Max Act: 4.1188. Min Act: -0.1700
Data Index: 2484965 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2438. Min Range: -4.2438
Max Act: 4.0250. Min Act: -0.1700
Data Index: 4114641 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2438. Min Range: -4.2438
Max Act: 4.0250. Min Act: -0.1700
Data Index: 7553518 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2438. Min Range: -4.2438
Max Act: 4.0250. Min Act: -0.1700
Data Index: 5281566 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2438. Min Range: -4.2438
Max Act: 3.9937. Min Act: -0.1700
Data Index: 5154499 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2438. Min Range: -4.2438
Max Act: 3.9937. Min Act: -0.1700
Data Index: 8646073 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2438. Min Range: -4.2438
Max Act: 3.9937. Min Act: -0.1700
Data Index: 306510 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2438. Min Range: -4.2438
Max Act: 3.9937. Min Act: -0.1700
Data Index: 2894679 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2438. Min Range: -4.2438
Max Act: 3.9625. Min Act: -0.1700
Data Index: 1624365 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2438. Min Range: -4.2438
Max Act: 3.9625. Min Act: -0.1700
Data Index: 5245278 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2438. Min Range: -4.2438
Max Act: 3.9312. Min Act: -0.1700
Data Index: 3937056 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2438. Min Range: -4.2438
Max Act: 3.9312. Min Act: -0.1700
Data Index: 333981 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2438. Min Range: -4.2438
Max Act: 3.9000. Min Act: -0.1700
Data Index: 82362 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2438. Min Range: -4.2438
Max Act: 3.9000. Min Act: -0.1700
Data Index: 7366998 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2438. Min Range: -4.2438
Max Act: 3.9000. Min Act: -0.1700
Data Index: 6963125 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2438. Min Range: -4.2438
Max Act: 3.9000. Min Act: -0.1700
Data Index: 3015119 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2438. Min Range: -4.2438
Max Act: 3.9000. Min Act: -0.1700
Data Index: 2211636 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #19