Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 371 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.3017. Min Range: -1.3017
Max Act: 1.3017. Min Act: -0.1700
Data Index: 2872153 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3017. Min Range: -1.3017
Max Act: 1.2841. Min Act: -0.1700
Data Index: 5262276 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3017. Min Range: -1.3017
Max Act: 1.2841. Min Act: -0.1700
Data Index: 5556991 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3017. Min Range: -1.3017
Max Act: 1.2576. Min Act: -0.1656
Data Index: 1159363 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3017. Min Range: -1.3017
Max Act: 1.2312. Min Act: -0.1700
Data Index: 3101229 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3017. Min Range: -1.3017
Max Act: 1.2224. Min Act: -0.1700
Data Index: 4017420 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3017. Min Range: -1.3017
Max Act: 1.2135. Min Act: -0.1699
Data Index: 2413758 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3017. Min Range: -1.3017
Max Act: 1.2224. Min Act: -0.1700
Data Index: 8477344 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3017. Min Range: -1.3017
Max Act: 1.2224. Min Act: -0.1699
Data Index: 6308586 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3017. Min Range: -1.3017
Max Act: 1.2135. Min Act: -0.1695
Data Index: 7899965 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3017. Min Range: -1.3017
Max Act: 1.2224. Min Act: -0.1607
Data Index: 6509765 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3017. Min Range: -1.3017
Max Act: 1.2047. Min Act: -0.1700
Data Index: 493756 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3017. Min Range: -1.3017
Max Act: 1.1959. Min Act: -0.1650
Data Index: 1714380 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3017. Min Range: -1.3017
Max Act: 1.2047. Min Act: -0.1699
Data Index: 493755 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3017. Min Range: -1.3017
Max Act: 1.2047. Min Act: -0.1699
Data Index: 575562 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3017. Min Range: -1.3017
Max Act: 1.2047. Min Act: -0.1697
Data Index: 7399988 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3017. Min Range: -1.3017
Max Act: 1.1871. Min Act: -0.1699
Data Index: 7483109 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3017. Min Range: -1.3017
Max Act: 1.1959. Min Act: -0.1670
Data Index: 4343448 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3017. Min Range: -1.3017
Max Act: 1.1959. Min Act: -0.1700
Data Index: 3086547 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3017. Min Range: -1.3017
Max Act: 1.1783. Min Act: -0.1697
Data Index: 1698727 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #19