Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0645. Min Range: -4.0645
Max Act: 4.0645. Min Act: -0.1700
Data Index: 5601956 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0645. Min Range: -4.0645
Max Act: 4.0332. Min Act: -0.1700
Data Index: 7435461 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0645. Min Range: -4.0645
Max Act: 4.0645. Min Act: -0.1700
Data Index: 472149 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0645. Min Range: -4.0645
Max Act: 4.0332. Min Act: -0.1700
Data Index: 1778417 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0645. Min Range: -4.0645
Max Act: 4.0020. Min Act: -0.1700
Data Index: 4733144 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0645. Min Range: -4.0645
Max Act: 4.0020. Min Act: -0.1700
Data Index: 5268674 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0645. Min Range: -4.0645
Max Act: 3.9707. Min Act: -0.1700
Data Index: 6501394 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0645. Min Range: -4.0645
Max Act: 3.9707. Min Act: -0.1700
Data Index: 7223579 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0645. Min Range: -4.0645
Max Act: 3.9707. Min Act: -0.1700
Data Index: 5430359 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0645. Min Range: -4.0645
Max Act: 3.9082. Min Act: -0.1700
Data Index: 6326408 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0645. Min Range: -4.0645
Max Act: 3.9395. Min Act: -0.1700
Data Index: 665781 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0645. Min Range: -4.0645
Max Act: 3.9395. Min Act: -0.1700
Data Index: 2931700 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0645. Min Range: -4.0645
Max Act: 3.9395. Min Act: -0.1700
Data Index: 1324634 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0645. Min Range: -4.0645
Max Act: 3.9395. Min Act: -0.1700
Data Index: 1260610 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0645. Min Range: -4.0645
Max Act: 3.9395. Min Act: -0.1700
Data Index: 8608995 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0645. Min Range: -4.0645
Max Act: 3.9395. Min Act: -0.1700
Data Index: 4327783 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0645. Min Range: -4.0645
Max Act: 3.9082. Min Act: -0.1700
Data Index: 1908305 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0645. Min Range: -4.0645
Max Act: 3.9082. Min Act: -0.1700
Data Index: 313954 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0645. Min Range: -4.0645
Max Act: 3.9082. Min Act: -0.1700
Data Index: 2604956 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0645. Min Range: -4.0645
Max Act: 3.9395. Min Act: -0.1700
Data Index: 1078277 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #19