Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2844 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.4314. Min Range: -2.4314
Max Act: 2.4314. Min Act: -0.1700
Data Index: 2276197 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4314. Min Range: -2.4314
Max Act: 2.3169. Min Act: -0.1700
Data Index: 7947214 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4314. Min Range: -2.4314
Max Act: 2.3004. Min Act: -0.1700
Data Index: 3039373 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4314. Min Range: -2.4314
Max Act: 2.3004. Min Act: -0.1700
Data Index: 115614 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4314. Min Range: -2.4314
Max Act: 2.3004. Min Act: -0.1700
Data Index: 1298535 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4314. Min Range: -2.4314
Max Act: 2.2675. Min Act: -0.1700
Data Index: 452834 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4314. Min Range: -2.4314
Max Act: 2.3004. Min Act: -0.1700
Data Index: 973075 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4314. Min Range: -2.4314
Max Act: 2.2840. Min Act: -0.1700
Data Index: 5436964 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4314. Min Range: -2.4314
Max Act: 2.2675. Min Act: -0.1700
Data Index: 1335721 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4314. Min Range: -2.4314
Max Act: 2.2510. Min Act: -0.1700
Data Index: 1130969 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4314. Min Range: -2.4314
Max Act: 2.2179. Min Act: -0.1700
Data Index: 4901700 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4314. Min Range: -2.4314
Max Act: 2.2179. Min Act: -0.1700
Data Index: 7869698 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4314. Min Range: -2.4314
Max Act: 2.1847. Min Act: -0.1700
Data Index: 5793354 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4314. Min Range: -2.4314
Max Act: 2.2344. Min Act: -0.1700
Data Index: 623049 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4314. Min Range: -2.4314
Max Act: 2.2013. Min Act: -0.1700
Data Index: 4113842 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4314. Min Range: -2.4314
Max Act: 2.2179. Min Act: -0.1700
Data Index: 7993045 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4314. Min Range: -2.4314
Max Act: 2.2179. Min Act: -0.1700
Data Index: 385855 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4314. Min Range: -2.4314
Max Act: 2.2013. Min Act: -0.1700
Data Index: 1677508 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4314. Min Range: -2.4314
Max Act: 2.2179. Min Act: -0.1700
Data Index: 2718316 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4314. Min Range: -2.4314
Max Act: 2.1681. Min Act: -0.1700
Data Index: 4138646 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #19