Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1436 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2179. Min Range: -3.2179
Max Act: 3.2179. Min Act: -0.1700
Data Index: 7028318 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2179. Min Range: -3.2179
Max Act: 3.1393. Min Act: -0.1700
Data Index: 2369808 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2179. Min Range: -3.2179
Max Act: 3.1235. Min Act: -0.1700
Data Index: 4879749 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2179. Min Range: -3.2179
Max Act: 3.1078. Min Act: -0.1700
Data Index: 5049633 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2179. Min Range: -3.2179
Max Act: 3.0289. Min Act: -0.1700
Data Index: 7253882 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2179. Min Range: -3.2179
Max Act: 3.0447. Min Act: -0.1700
Data Index: 3833667 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2179. Min Range: -3.2179
Max Act: 3.0763. Min Act: -0.1700
Data Index: 7184622 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2179. Min Range: -3.2179
Max Act: 3.0289. Min Act: -0.1700
Data Index: 1317832 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2179. Min Range: -3.2179
Max Act: 3.0131. Min Act: -0.1700
Data Index: 7028319 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2179. Min Range: -3.2179
Max Act: 2.9815. Min Act: -0.1700
Data Index: 4269135 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2179. Min Range: -3.2179
Max Act: 2.9815. Min Act: -0.1700
Data Index: 7277528 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2179. Min Range: -3.2179
Max Act: 2.9815. Min Act: -0.1700
Data Index: 4984997 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2179. Min Range: -3.2179
Max Act: 2.9499. Min Act: -0.1700
Data Index: 7601526 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2179. Min Range: -3.2179
Max Act: 2.9340. Min Act: -0.1700
Data Index: 569971 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2179. Min Range: -3.2179
Max Act: 2.9023. Min Act: -0.1700
Data Index: 4743056 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2179. Min Range: -3.2179
Max Act: 2.9023. Min Act: -0.1700
Data Index: 6715155 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2179. Min Range: -3.2179
Max Act: 2.8865. Min Act: -0.1700
Data Index: 5049632 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2179. Min Range: -3.2179
Max Act: 2.8706. Min Act: -0.1700
Data Index: 492164 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2179. Min Range: -3.2179
Max Act: 2.8706. Min Act: -0.1700
Data Index: 2926520 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2179. Min Range: -3.2179
Max Act: 2.8547. Min Act: -0.1700
Data Index: 6821134 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #19