Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 970 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3487. Min Range: -8.3487
Max Act: 8.3487. Min Act: -0.1700
Data Index: 2579198 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3487. Min Range: -8.3487
Max Act: 8.0362. Min Act: -0.1700
Data Index: 5042574 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3487. Min Range: -8.3487
Max Act: 7.9112. Min Act: -0.1700
Data Index: 5042577 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3487. Min Range: -8.3487
Max Act: 7.9112. Min Act: -0.1700
Data Index: 5042570 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3487. Min Range: -8.3487
Max Act: 7.7237. Min Act: -0.1700
Data Index: 5042571 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3487. Min Range: -8.3487
Max Act: 7.7237. Min Act: -0.1700
Data Index: 5645033 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3487. Min Range: -8.3487
Max Act: 7.5987. Min Act: -0.1700
Data Index: 6746061 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3487. Min Range: -8.3487
Max Act: 7.5987. Min Act: -0.1700
Data Index: 5042573 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3487. Min Range: -8.3487
Max Act: 7.5987. Min Act: -0.1700
Data Index: 8569789 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3487. Min Range: -8.3487
Max Act: 7.5675. Min Act: -0.1700
Data Index: 811305 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3487. Min Range: -8.3487
Max Act: 7.5987. Min Act: -0.1700
Data Index: 5042572 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3487. Min Range: -8.3487
Max Act: 7.5050. Min Act: -0.1700
Data Index: 5024982 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3487. Min Range: -8.3487
Max Act: 7.4737. Min Act: -0.1700
Data Index: 5042576 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3487. Min Range: -8.3487
Max Act: 7.4737. Min Act: -0.1700
Data Index: 5645036 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3487. Min Range: -8.3487
Max Act: 7.4737. Min Act: -0.1700
Data Index: 5042578 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3487. Min Range: -8.3487
Max Act: 7.4112. Min Act: -0.1700
Data Index: 5645034 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3487. Min Range: -8.3487
Max Act: 7.4112. Min Act: -0.1700
Data Index: 4021615 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3487. Min Range: -8.3487
Max Act: 7.4112. Min Act: -0.1700
Data Index: 2551112 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3487. Min Range: -8.3487
Max Act: 7.4112. Min Act: -0.1700
Data Index: 7431948 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3487. Min Range: -8.3487
Max Act: 7.3800. Min Act: -0.1700
Data Index: 5042566 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #19