Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1914 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 16.1764. Min Range: -16.1764
Max Act: 16.1764. Min Act: -0.1700
Data Index: 6228460 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 16.1764. Min Range: -16.1764
Max Act: 15.9264. Min Act: -0.1700
Data Index: 1702646 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 16.1764. Min Range: -16.1764
Max Act: 15.6764. Min Act: -0.1700
Data Index: 3433501 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 16.1764. Min Range: -16.1764
Max Act: 15.4264. Min Act: -0.1700
Data Index: 644245 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 16.1764. Min Range: -16.1764
Max Act: 15.3639. Min Act: -0.1700
Data Index: 644244 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 16.1764. Min Range: -16.1764
Max Act: 15.4889. Min Act: -0.1700
Data Index: 2079454 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 16.1764. Min Range: -16.1764
Max Act: 15.3014. Min Act: -0.1700
Data Index: 8257316 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 16.1764. Min Range: -16.1764
Max Act: 15.1764. Min Act: -0.1700
Data Index: 5382022 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 16.1764. Min Range: -16.1764
Max Act: 15.1764. Min Act: -0.1700
Data Index: 3737704 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 16.1764. Min Range: -16.1764
Max Act: 15.1764. Min Act: -0.1700
Data Index: 4190573 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 16.1764. Min Range: -16.1764
Max Act: 15.1139. Min Act: -0.1700
Data Index: 8794517 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 16.1764. Min Range: -16.1764
Max Act: 15.1139. Min Act: -0.1700
Data Index: 967400 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 16.1764. Min Range: -16.1764
Max Act: 15.0514. Min Act: -0.1700
Data Index: 4039086 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 16.1764. Min Range: -16.1764
Max Act: 15.1139. Min Act: -0.1700
Data Index: 8794515 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 16.1764. Min Range: -16.1764
Max Act: 15.0514. Min Act: -0.1700
Data Index: 2245224 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 16.1764. Min Range: -16.1764
Max Act: 15.1139. Min Act: -0.1700
Data Index: 7244907 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 16.1764. Min Range: -16.1764
Max Act: 15.1139. Min Act: -0.1700
Data Index: 8762657 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 16.1764. Min Range: -16.1764
Max Act: 14.9889. Min Act: -0.1700
Data Index: 5716681 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 16.1764. Min Range: -16.1764
Max Act: 14.9889. Min Act: -0.1700
Data Index: 2244983 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 16.1764. Min Range: -16.1764
Max Act: 14.9889. Min Act: -0.1700
Data Index: 3167356 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #19