Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 201 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.3700. Min Range: -5.3700
Max Act: 5.3700. Min Act: -0.1700
Data Index: 8570198 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3700. Min Range: -5.3700
Max Act: 5.2137. Min Act: -0.1700
Data Index: 4219432 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3700. Min Range: -5.3700
Max Act: 5.1512. Min Act: -0.1700
Data Index: 5741301 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3700. Min Range: -5.3700
Max Act: 5.0575. Min Act: -0.1700
Data Index: 5393027 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3700. Min Range: -5.3700
Max Act: 5.0887. Min Act: -0.1700
Data Index: 393846 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3700. Min Range: -5.3700
Max Act: 5.0575. Min Act: -0.1700
Data Index: 2852349 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3700. Min Range: -5.3700
Max Act: 5.0575. Min Act: -0.1700
Data Index: 5630244 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3700. Min Range: -5.3700
Max Act: 5.0262. Min Act: -0.1700
Data Index: 2867645 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3700. Min Range: -5.3700
Max Act: 4.9950. Min Act: -0.1700
Data Index: 8077757 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3700. Min Range: -5.3700
Max Act: 4.9950. Min Act: -0.1700
Data Index: 2577060 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3700. Min Range: -5.3700
Max Act: 4.9950. Min Act: -0.1700
Data Index: 1199125 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3700. Min Range: -5.3700
Max Act: 4.9950. Min Act: -0.1700
Data Index: 7002000 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3700. Min Range: -5.3700
Max Act: 4.9950. Min Act: -0.1700
Data Index: 3091999 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3700. Min Range: -5.3700
Max Act: 4.9637. Min Act: -0.1700
Data Index: 7798650 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3700. Min Range: -5.3700
Max Act: 4.9637. Min Act: -0.1700
Data Index: 2428429 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3700. Min Range: -5.3700
Max Act: 4.9325. Min Act: -0.1700
Data Index: 7123675 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3700. Min Range: -5.3700
Max Act: 4.9325. Min Act: -0.1700
Data Index: 2761049 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3700. Min Range: -5.3700
Max Act: 4.9325. Min Act: -0.1700
Data Index: 5670155 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3700. Min Range: -5.3700
Max Act: 4.9012. Min Act: -0.1700
Data Index: 3455059 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3700. Min Range: -5.3700
Max Act: 4.9012. Min Act: -0.1700
Data Index: 436727 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #19