Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1103 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.0931. Min Range: -3.0931
Max Act: 3.0615. Min Act: -0.1700
Data Index: 2535669 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0931. Min Range: -3.0931
Max Act: 3.0931. Min Act: -0.1700
Data Index: 8185353 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0931. Min Range: -3.0931
Max Act: 3.0615. Min Act: -0.1700
Data Index: 6488443 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0931. Min Range: -3.0931
Max Act: 3.0142. Min Act: -0.1700
Data Index: 4536321 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0931. Min Range: -3.0931
Max Act: 2.9034. Min Act: -0.1700
Data Index: 5469612 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0931. Min Range: -3.0931
Max Act: 2.8716. Min Act: -0.1700
Data Index: 4528718 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0931. Min Range: -3.0931
Max Act: 2.8716. Min Act: -0.1700
Data Index: 2435410 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0931. Min Range: -3.0931
Max Act: 2.8875. Min Act: -0.1700
Data Index: 8234091 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0931. Min Range: -3.0931
Max Act: 2.8875. Min Act: -0.1700
Data Index: 31021 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0931. Min Range: -3.0931
Max Act: 2.8399. Min Act: -0.1700
Data Index: 6498988 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0931. Min Range: -3.0931
Max Act: 2.8716. Min Act: -0.1700
Data Index: 3318959 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0931. Min Range: -3.0931
Max Act: 2.8716. Min Act: -0.1700
Data Index: 2409380 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0931. Min Range: -3.0931
Max Act: 2.8875. Min Act: -0.1700
Data Index: 3578773 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0931. Min Range: -3.0931
Max Act: 2.8240. Min Act: -0.1700
Data Index: 8552193 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0931. Min Range: -3.0931
Max Act: 2.8558. Min Act: -0.1700
Data Index: 4927578 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0931. Min Range: -3.0931
Max Act: 2.8399. Min Act: -0.1700
Data Index: 2410894 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0931. Min Range: -3.0931
Max Act: 2.8399. Min Act: -0.1700
Data Index: 2409370 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0931. Min Range: -3.0931
Max Act: 2.8558. Min Act: -0.1700
Data Index: 5721360 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0931. Min Range: -3.0931
Max Act: 2.8558. Min Act: -0.1700
Data Index: 8105963 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0931. Min Range: -3.0931
Max Act: 2.7921. Min Act: -0.1700
Data Index: 5095708 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #19