Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4538 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4518. Min Range: -7.4518
Max Act: 7.4518. Min Act: -0.1700
Data Index: 6314855 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4518. Min Range: -7.4518
Max Act: 7.3893. Min Act: -0.1700
Data Index: 1736756 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4518. Min Range: -7.4518
Max Act: 7.2956. Min Act: -0.1700
Data Index: 8094136 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4518. Min Range: -7.4518
Max Act: 7.2956. Min Act: -0.1700
Data Index: 3623684 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4518. Min Range: -7.4518
Max Act: 7.2643. Min Act: -0.1700
Data Index: 831991 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4518. Min Range: -7.4518
Max Act: 7.2643. Min Act: -0.1700
Data Index: 7481215 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4518. Min Range: -7.4518
Max Act: 7.2331. Min Act: -0.1700
Data Index: 5729449 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4518. Min Range: -7.4518
Max Act: 7.2331. Min Act: -0.1700
Data Index: 183257 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4518. Min Range: -7.4518
Max Act: 7.1706. Min Act: -0.1700
Data Index: 1928298 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4518. Min Range: -7.4518
Max Act: 7.1393. Min Act: -0.1700
Data Index: 2909219 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4518. Min Range: -7.4518
Max Act: 7.1393. Min Act: -0.1700
Data Index: 7049345 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4518. Min Range: -7.4518
Max Act: 7.1081. Min Act: -0.1700
Data Index: 1919629 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4518. Min Range: -7.4518
Max Act: 7.1081. Min Act: -0.1700
Data Index: 7049344 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4518. Min Range: -7.4518
Max Act: 7.0768. Min Act: -0.1700
Data Index: 7696317 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4518. Min Range: -7.4518
Max Act: 7.0768. Min Act: -0.1700
Data Index: 1473412 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4518. Min Range: -7.4518
Max Act: 7.0768. Min Act: -0.1700
Data Index: 5496826 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4518. Min Range: -7.4518
Max Act: 7.0456. Min Act: -0.1700
Data Index: 1539118 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4518. Min Range: -7.4518
Max Act: 7.0768. Min Act: -0.1700
Data Index: 5843522 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4518. Min Range: -7.4518
Max Act: 7.0143. Min Act: -0.1700
Data Index: 3014320 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4518. Min Range: -7.4518
Max Act: 6.9831. Min Act: -0.1700
Data Index: 2602653 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #19