Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2345 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.0165. Min Range: -3.0165
Max Act: 3.0165. Min Act: -0.1700
Data Index: 6942441 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0165. Min Range: -3.0165
Max Act: 2.9849. Min Act: -0.1700
Data Index: 2425103 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0165. Min Range: -3.0165
Max Act: 2.9375. Min Act: -0.1700
Data Index: 5133999 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0165. Min Range: -3.0165
Max Act: 2.9058. Min Act: -0.1700
Data Index: 4971444 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0165. Min Range: -3.0165
Max Act: 2.8899. Min Act: -0.1700
Data Index: 6332172 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0165. Min Range: -3.0165
Max Act: 2.8582. Min Act: -0.1700
Data Index: 5712194 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0165. Min Range: -3.0165
Max Act: 2.8423. Min Act: -0.1700
Data Index: 2420087 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0165. Min Range: -3.0165
Max Act: 2.8582. Min Act: -0.1700
Data Index: 1099877 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0165. Min Range: -3.0165
Max Act: 2.8423. Min Act: -0.1700
Data Index: 8231678 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0165. Min Range: -3.0165
Max Act: 2.8264. Min Act: -0.1700
Data Index: 5466451 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0165. Min Range: -3.0165
Max Act: 2.8264. Min Act: -0.1700
Data Index: 3370450 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0165. Min Range: -3.0165
Max Act: 2.8105. Min Act: -0.1700
Data Index: 7424152 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0165. Min Range: -3.0165
Max Act: 2.7786. Min Act: -0.1700
Data Index: 2079021 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0165. Min Range: -3.0165
Max Act: 2.8105. Min Act: -0.1700
Data Index: 4417791 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0165. Min Range: -3.0165
Max Act: 2.7786. Min Act: -0.1700
Data Index: 2477346 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0165. Min Range: -3.0165
Max Act: 2.7627. Min Act: -0.1700
Data Index: 4417943 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0165. Min Range: -3.0165
Max Act: 2.7627. Min Act: -0.1700
Data Index: 1864852 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0165. Min Range: -3.0165
Max Act: 2.7627. Min Act: -0.1700
Data Index: 2623574 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0165. Min Range: -3.0165
Max Act: 2.7627. Min Act: -0.1700
Data Index: 3618489 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0165. Min Range: -3.0165
Max Act: 2.7307. Min Act: -0.1700
Data Index: 3507329 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #19