Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 728 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3163. Min Range: -4.3163
Max Act: 4.3163. Min Act: -0.1700
Data Index: 1582027 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3163. Min Range: -4.3163
Max Act: 4.3163. Min Act: -0.1700
Data Index: 5163701 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3163. Min Range: -4.3163
Max Act: 4.2225. Min Act: -0.1700
Data Index: 5219362 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3163. Min Range: -4.3163
Max Act: 4.2225. Min Act: -0.1700
Data Index: 2762821 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3163. Min Range: -4.3163
Max Act: 4.2225. Min Act: -0.1700
Data Index: 7114759 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3163. Min Range: -4.3163
Max Act: 4.1913. Min Act: -0.1700
Data Index: 7385682 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3163. Min Range: -4.3163
Max Act: 4.1913. Min Act: -0.1700
Data Index: 2292232 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3163. Min Range: -4.3163
Max Act: 4.1600. Min Act: -0.1700
Data Index: 2145640 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3163. Min Range: -4.3163
Max Act: 4.1600. Min Act: -0.1700
Data Index: 1705657 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3163. Min Range: -4.3163
Max Act: 4.1600. Min Act: -0.1700
Data Index: 382258 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3163. Min Range: -4.3163
Max Act: 4.1600. Min Act: -0.1700
Data Index: 1634984 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3163. Min Range: -4.3163
Max Act: 4.1600. Min Act: -0.1700
Data Index: 786040 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3163. Min Range: -4.3163
Max Act: 4.1600. Min Act: -0.1700
Data Index: 890942 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3163. Min Range: -4.3163
Max Act: 4.1600. Min Act: -0.1695
Data Index: 1044541 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3163. Min Range: -4.3163
Max Act: 4.1600. Min Act: -0.1700
Data Index: 884345 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3163. Min Range: -4.3163
Max Act: 4.1600. Min Act: -0.1700
Data Index: 464893 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3163. Min Range: -4.3163
Max Act: 4.1600. Min Act: -0.1700
Data Index: 1939711 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3163. Min Range: -4.3163
Max Act: 4.1600. Min Act: -0.1699
Data Index: 896334 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3163. Min Range: -4.3163
Max Act: 4.1600. Min Act: -0.1700
Data Index: 2127980 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3163. Min Range: -4.3163
Max Act: 4.1600. Min Act: -0.1700
Data Index: 219944 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19