Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 938 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6258. Min Range: -5.6258
Max Act: 5.6258. Min Act: -0.1700
Data Index: 8288102 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6258. Min Range: -5.6258
Max Act: 5.3446. Min Act: -0.1700
Data Index: 6118931 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6258. Min Range: -5.6258
Max Act: 5.3133. Min Act: -0.1700
Data Index: 4956427 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6258. Min Range: -5.6258
Max Act: 5.2508. Min Act: -0.1700
Data Index: 3138961 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6258. Min Range: -5.6258
Max Act: 5.2821. Min Act: -0.1700
Data Index: 7083136 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6258. Min Range: -5.6258
Max Act: 5.2821. Min Act: -0.1700
Data Index: 86026 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6258. Min Range: -5.6258
Max Act: 5.2508. Min Act: -0.1700
Data Index: 4198303 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6258. Min Range: -5.6258
Max Act: 5.2508. Min Act: -0.1700
Data Index: 5233350 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6258. Min Range: -5.6258
Max Act: 5.2196. Min Act: -0.1700
Data Index: 1899892 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6258. Min Range: -5.6258
Max Act: 5.2196. Min Act: -0.1700
Data Index: 8038604 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6258. Min Range: -5.6258
Max Act: 5.2508. Min Act: -0.1700
Data Index: 4240066 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6258. Min Range: -5.6258
Max Act: 5.1571. Min Act: -0.1700
Data Index: 152436 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6258. Min Range: -5.6258
Max Act: 5.1883. Min Act: -0.1700
Data Index: 7083130 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6258. Min Range: -5.6258
Max Act: 5.1883. Min Act: -0.1700
Data Index: 7039478 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6258. Min Range: -5.6258
Max Act: 5.1883. Min Act: -0.1700
Data Index: 6307515 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6258. Min Range: -5.6258
Max Act: 5.1883. Min Act: -0.1700
Data Index: 8323543 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6258. Min Range: -5.6258
Max Act: 5.1883. Min Act: -0.1700
Data Index: 5357500 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6258. Min Range: -5.6258
Max Act: 5.1571. Min Act: -0.1700
Data Index: 5313434 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6258. Min Range: -5.6258
Max Act: 5.1571. Min Act: -0.1700
Data Index: 7583018 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6258. Min Range: -5.6258
Max Act: 5.0946. Min Act: -0.1700
Data Index: 2757256 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #19