Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3427 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.1138. Min Range: -10.1138
Max Act: 10.1138. Min Act: -0.1700
Data Index: 6349270 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.1138. Min Range: -10.1138
Max Act: 9.9888. Min Act: -0.1700
Data Index: 5716563 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.1138. Min Range: -10.1138
Max Act: 9.8013. Min Act: -0.1700
Data Index: 2130744 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.1138. Min Range: -10.1138
Max Act: 9.8013. Min Act: -0.1700
Data Index: 2728221 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.1138. Min Range: -10.1138
Max Act: 9.5513. Min Act: -0.1700
Data Index: 7107598 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.1138. Min Range: -10.1138
Max Act: 9.5513. Min Act: -0.1700
Data Index: 1913599 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.1138. Min Range: -10.1138
Max Act: 9.4888. Min Act: -0.1700
Data Index: 3586269 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.1138. Min Range: -10.1138
Max Act: 9.4888. Min Act: -0.1700
Data Index: 6562977 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.1138. Min Range: -10.1138
Max Act: 9.4263. Min Act: -0.1700
Data Index: 8341742 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.1138. Min Range: -10.1138
Max Act: 9.4263. Min Act: -0.1700
Data Index: 2115858 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.1138. Min Range: -10.1138
Max Act: 9.4263. Min Act: -0.1700
Data Index: 5731309 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.1138. Min Range: -10.1138
Max Act: 9.4263. Min Act: -0.1700
Data Index: 3321479 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.1138. Min Range: -10.1138
Max Act: 9.4263. Min Act: -0.1700
Data Index: 268704 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.1138. Min Range: -10.1138
Max Act: 9.4263. Min Act: -0.1700
Data Index: 2424844 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.1138. Min Range: -10.1138
Max Act: 9.3638. Min Act: -0.1700
Data Index: 3939826 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.1138. Min Range: -10.1138
Max Act: 9.3013. Min Act: -0.1700
Data Index: 3383184 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.1138. Min Range: -10.1138
Max Act: 9.3638. Min Act: -0.1700
Data Index: 148489 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.1138. Min Range: -10.1138
Max Act: 9.3013. Min Act: -0.1700
Data Index: 594823 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.1138. Min Range: -10.1138
Max Act: 9.2388. Min Act: -0.1700
Data Index: 7167955 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.1138. Min Range: -10.1138
Max Act: 9.3013. Min Act: -0.1700
Data Index: 2158143 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #19