Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 643 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.8893. Min Range: -9.8893
Max Act: 8.7018. Min Act: -0.1700
Data Index: 8390091 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8893. Min Range: -9.8893
Max Act: 9.8893. Min Act: -0.1700
Data Index: 5565136 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8893. Min Range: -9.8893
Max Act: 7.4206. Min Act: -0.1700
Data Index: 3186847 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8893. Min Range: -9.8893
Max Act: 8.8893. Min Act: -0.1700
Data Index: 5565126 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8893. Min Range: -9.8893
Max Act: 7.4831. Min Act: -0.1700
Data Index: 4894525 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8893. Min Range: -9.8893
Max Act: 8.8893. Min Act: -0.1700
Data Index: 6209040 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8893. Min Range: -9.8893
Max Act: 7.9206. Min Act: -0.1700
Data Index: 2808921 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8893. Min Range: -9.8893
Max Act: 5.9206. Min Act: -0.1700
Data Index: 6923826 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8893. Min Range: -9.8893
Max Act: 6.3581. Min Act: -0.1700
Data Index: 4490802 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8893. Min Range: -9.8893
Max Act: 7.7643. Min Act: -0.1700
Data Index: 825490 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8893. Min Range: -9.8893
Max Act: 5.1081. Min Act: -0.1700
Data Index: 3549092 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8893. Min Range: -9.8893
Max Act: 7.7018. Min Act: -0.1700
Data Index: 8390092 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8893. Min Range: -9.8893
Max Act: 6.8581. Min Act: -0.1700
Data Index: 88723 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8893. Min Range: -9.8893
Max Act: 7.6393. Min Act: -0.1700
Data Index: 2041033 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8893. Min Range: -9.8893
Max Act: 7.0456. Min Act: -0.1700
Data Index: 1171368 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8893. Min Range: -9.8893
Max Act: 5.4831. Min Act: -0.1700
Data Index: 1896204 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8893. Min Range: -9.8893
Max Act: 7.5456. Min Act: -0.1700
Data Index: 733244 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8893. Min Range: -9.8893
Max Act: 5.4206. Min Act: -0.1700
Data Index: 7355354 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8893. Min Range: -9.8893
Max Act: 7.5456. Min Act: -0.1700
Data Index: 3645984 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8893. Min Range: -9.8893
Max Act: 7.5768. Min Act: -0.1700
Data Index: 3290119 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #19