Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2937 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3706. Min Range: -9.3706
Max Act: 9.3706. Min Act: -0.1700
Data Index: 3077799 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3706. Min Range: -9.3706
Max Act: 9.3081. Min Act: -0.1700
Data Index: 1215823 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3706. Min Range: -9.3706
Max Act: 8.9956. Min Act: -0.1700
Data Index: 2160770 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3706. Min Range: -9.3706
Max Act: 8.9331. Min Act: -0.1700
Data Index: 3942571 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3706. Min Range: -9.3706
Max Act: 8.9331. Min Act: -0.1700
Data Index: 6689151 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3706. Min Range: -9.3706
Max Act: 8.9331. Min Act: -0.1700
Data Index: 6266609 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3706. Min Range: -9.3706
Max Act: 8.8706. Min Act: -0.1700
Data Index: 2576264 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3706. Min Range: -9.3706
Max Act: 8.8706. Min Act: -0.1700
Data Index: 4054494 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3706. Min Range: -9.3706
Max Act: 8.8081. Min Act: -0.1700
Data Index: 3852789 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3706. Min Range: -9.3706
Max Act: 8.7456. Min Act: -0.1700
Data Index: 6300668 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3706. Min Range: -9.3706
Max Act: 8.7456. Min Act: -0.1700
Data Index: 3098355 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3706. Min Range: -9.3706
Max Act: 8.6831. Min Act: -0.1700
Data Index: 885069 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3706. Min Range: -9.3706
Max Act: 8.6831. Min Act: -0.1700
Data Index: 528569 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3706. Min Range: -9.3706
Max Act: 8.6831. Min Act: -0.1700
Data Index: 503416 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3706. Min Range: -9.3706
Max Act: 8.7456. Min Act: -0.1700
Data Index: 3837388 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3706. Min Range: -9.3706
Max Act: 8.6831. Min Act: -0.1700
Data Index: 8634906 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3706. Min Range: -9.3706
Max Act: 8.6206. Min Act: -0.1700
Data Index: 7101586 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3706. Min Range: -9.3706
Max Act: 8.6206. Min Act: -0.1700
Data Index: 50650 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3706. Min Range: -9.3706
Max Act: 8.6206. Min Act: -0.1700
Data Index: 5794249 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3706. Min Range: -9.3706
Max Act: 8.5581. Min Act: -0.1700
Data Index: 1506833 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #19