Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2463 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2402. Min Range: -4.2402
Max Act: 4.2402. Min Act: -0.1700
Data Index: 3664513 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2402. Min Range: -4.2402
Max Act: 3.8964. Min Act: -0.1700
Data Index: 5782941 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2402. Min Range: -4.2402
Max Act: 3.9277. Min Act: -0.1700
Data Index: 6163726 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2402. Min Range: -4.2402
Max Act: 3.8964. Min Act: -0.1700
Data Index: 6768450 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2402. Min Range: -4.2402
Max Act: 3.8964. Min Act: -0.1700
Data Index: 8727721 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2402. Min Range: -4.2402
Max Act: 3.8964. Min Act: -0.1700
Data Index: 2475811 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2402. Min Range: -4.2402
Max Act: 3.8964. Min Act: -0.1700
Data Index: 3522108 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2402. Min Range: -4.2402
Max Act: 3.8651. Min Act: -0.1700
Data Index: 6749626 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2402. Min Range: -4.2402
Max Act: 3.8339. Min Act: -0.1700
Data Index: 7367639 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2402. Min Range: -4.2402
Max Act: 3.8339. Min Act: -0.1700
Data Index: 545606 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2402. Min Range: -4.2402
Max Act: 3.8026. Min Act: -0.1700
Data Index: 4891715 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2402. Min Range: -4.2402
Max Act: 3.8026. Min Act: -0.1700
Data Index: 5262602 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2402. Min Range: -4.2402
Max Act: 3.7713. Min Act: -0.1700
Data Index: 1103886 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2402. Min Range: -4.2402
Max Act: 3.8026. Min Act: -0.1700
Data Index: 8554645 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2402. Min Range: -4.2402
Max Act: 3.7400. Min Act: -0.1700
Data Index: 2920782 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2402. Min Range: -4.2402
Max Act: 3.7400. Min Act: -0.1700
Data Index: 390667 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2402. Min Range: -4.2402
Max Act: 3.7713. Min Act: -0.1700
Data Index: 4186238 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2402. Min Range: -4.2402
Max Act: 3.7400. Min Act: -0.1700
Data Index: 1203706 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2402. Min Range: -4.2402
Max Act: 3.7713. Min Act: -0.1700
Data Index: 6248443 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2402. Min Range: -4.2402
Max Act: 3.7713. Min Act: -0.1700
Data Index: 6401725 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #19