Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4861 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.2268. Min Range: -2.2268
Max Act: 2.2268. Min Act: -0.1699
Data Index: 5088826 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2268. Min Range: -2.2268
Max Act: 2.1270. Min Act: -0.1700
Data Index: 7782478 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2268. Min Range: -2.2268
Max Act: 2.1270. Min Act: -0.1700
Data Index: 7598984 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2268. Min Range: -2.2268
Max Act: 2.1103. Min Act: -0.1700
Data Index: 4623796 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2268. Min Range: -2.2268
Max Act: 2.1103. Min Act: -0.1700
Data Index: 1360112 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2268. Min Range: -2.2268
Max Act: 2.1103. Min Act: -0.1700
Data Index: 1926391 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2268. Min Range: -2.2268
Max Act: 2.0768. Min Act: -0.1700
Data Index: 2707768 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2268. Min Range: -2.2268
Max Act: 2.0768. Min Act: -0.1700
Data Index: 5866348 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2268. Min Range: -2.2268
Max Act: 2.0600. Min Act: -0.1700
Data Index: 3133166 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2268. Min Range: -2.2268
Max Act: 2.0600. Min Act: -0.1700
Data Index: 7480506 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2268. Min Range: -2.2268
Max Act: 2.0600. Min Act: -0.1700
Data Index: 2018552 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2268. Min Range: -2.2268
Max Act: 2.0263. Min Act: -0.1700
Data Index: 2313636 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2268. Min Range: -2.2268
Max Act: 2.0432. Min Act: -0.1700
Data Index: 2196638 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2268. Min Range: -2.2268
Max Act: 2.0432. Min Act: -0.1700
Data Index: 3914489 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2268. Min Range: -2.2268
Max Act: 2.0263. Min Act: -0.1699
Data Index: 6847212 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2268. Min Range: -2.2268
Max Act: 2.0263. Min Act: -0.1700
Data Index: 5067961 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2268. Min Range: -2.2268
Max Act: 2.0263. Min Act: -0.1700
Data Index: 4982201 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2268. Min Range: -2.2268
Max Act: 2.0263. Min Act: -0.1700
Data Index: 5266197 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2268. Min Range: -2.2268
Max Act: 2.0263. Min Act: -0.1700
Data Index: 3064187 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2268. Min Range: -2.2268
Max Act: 2.0432. Min Act: -0.1700
Data Index: 4410028 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #19