Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2686 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.6195. Min Range: -6.6195
Max Act: 6.6195. Min Act: -0.1700
Data Index: 396954 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6195. Min Range: -6.6195
Max Act: 6.5258. Min Act: -0.1700
Data Index: 3312157 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6195. Min Range: -6.6195
Max Act: 6.4633. Min Act: -0.1700
Data Index: 7531627 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6195. Min Range: -6.6195
Max Act: 6.4320. Min Act: -0.1700
Data Index: 2891603 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6195. Min Range: -6.6195
Max Act: 6.3695. Min Act: -0.1700
Data Index: 7619955 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6195. Min Range: -6.6195
Max Act: 6.3070. Min Act: -0.1700
Data Index: 7876337 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6195. Min Range: -6.6195
Max Act: 6.3070. Min Act: -0.1700
Data Index: 4267620 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6195. Min Range: -6.6195
Max Act: 6.2758. Min Act: -0.1700
Data Index: 7906190 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6195. Min Range: -6.6195
Max Act: 6.2758. Min Act: -0.1700
Data Index: 2369170 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6195. Min Range: -6.6195
Max Act: 6.3070. Min Act: -0.1700
Data Index: 1719668 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6195. Min Range: -6.6195
Max Act: 6.2445. Min Act: -0.1700
Data Index: 3024655 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6195. Min Range: -6.6195
Max Act: 6.2445. Min Act: -0.1700
Data Index: 5281596 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6195. Min Range: -6.6195
Max Act: 6.2133. Min Act: -0.1700
Data Index: 7827782 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6195. Min Range: -6.6195
Max Act: 6.2133. Min Act: -0.1700
Data Index: 1681388 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6195. Min Range: -6.6195
Max Act: 6.1820. Min Act: -0.1700
Data Index: 4287694 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6195. Min Range: -6.6195
Max Act: 6.1820. Min Act: -0.1700
Data Index: 8311934 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6195. Min Range: -6.6195
Max Act: 6.1820. Min Act: -0.1700
Data Index: 4286906 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6195. Min Range: -6.6195
Max Act: 6.1820. Min Act: -0.1700
Data Index: 3954524 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6195. Min Range: -6.6195
Max Act: 6.1508. Min Act: -0.1700
Data Index: 3169982 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6195. Min Range: -6.6195
Max Act: 6.1508. Min Act: -0.1700
Data Index: 6640597 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #19