Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3485 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4893. Min Range: -6.4893
Max Act: 6.4893. Min Act: -0.1700
Data Index: 5530190 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4893. Min Range: -6.4893
Max Act: 6.4268. Min Act: -0.1700
Data Index: 4760290 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4893. Min Range: -6.4893
Max Act: 6.4268. Min Act: -0.1700
Data Index: 2146935 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4893. Min Range: -6.4893
Max Act: 6.3331. Min Act: -0.1700
Data Index: 122563 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4893. Min Range: -6.4893
Max Act: 6.2706. Min Act: -0.1700
Data Index: 375352 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4893. Min Range: -6.4893
Max Act: 6.2706. Min Act: -0.1700
Data Index: 3370343 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4893. Min Range: -6.4893
Max Act: 6.2706. Min Act: -0.1700
Data Index: 8133526 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4893. Min Range: -6.4893
Max Act: 6.2393. Min Act: -0.1700
Data Index: 4029672 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4893. Min Range: -6.4893
Max Act: 6.2706. Min Act: -0.1700
Data Index: 8713167 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4893. Min Range: -6.4893
Max Act: 6.2081. Min Act: -0.1700
Data Index: 4205731 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4893. Min Range: -6.4893
Max Act: 6.2081. Min Act: -0.1700
Data Index: 4297750 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4893. Min Range: -6.4893
Max Act: 6.1768. Min Act: -0.1700
Data Index: 1569347 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4893. Min Range: -6.4893
Max Act: 6.1768. Min Act: -0.1700
Data Index: 8128703 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4893. Min Range: -6.4893
Max Act: 6.1768. Min Act: -0.1700
Data Index: 5971342 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4893. Min Range: -6.4893
Max Act: 6.1456. Min Act: -0.1700
Data Index: 8774257 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4893. Min Range: -6.4893
Max Act: 6.1768. Min Act: -0.1700
Data Index: 7082200 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4893. Min Range: -6.4893
Max Act: 6.1768. Min Act: -0.1700
Data Index: 6916804 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4893. Min Range: -6.4893
Max Act: 6.1456. Min Act: -0.1700
Data Index: 4673467 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4893. Min Range: -6.4893
Max Act: 6.0831. Min Act: -0.1700
Data Index: 608753 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4893. Min Range: -6.4893
Max Act: 6.0831. Min Act: -0.1700
Data Index: 922780 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #19