Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6194 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1317. Min Range: -8.1317
Max Act: 8.1317. Min Act: -0.1700
Data Index: 1516060 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1317. Min Range: -8.1317
Max Act: 7.6317. Min Act: -0.1700
Data Index: 5817813 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1317. Min Range: -8.1317
Max Act: 7.6004. Min Act: -0.1700
Data Index: 6289069 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1317. Min Range: -8.1317
Max Act: 7.5692. Min Act: -0.1700
Data Index: 7546120 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1317. Min Range: -8.1317
Max Act: 7.5067. Min Act: -0.1700
Data Index: 8244755 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1317. Min Range: -8.1317
Max Act: 7.4754. Min Act: -0.1700
Data Index: 2641377 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1317. Min Range: -8.1317
Max Act: 7.4442. Min Act: -0.1700
Data Index: 2740159 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1317. Min Range: -8.1317
Max Act: 7.4442. Min Act: -0.1700
Data Index: 3749154 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1317. Min Range: -8.1317
Max Act: 7.4129. Min Act: -0.1700
Data Index: 5001768 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1317. Min Range: -8.1317
Max Act: 7.3817. Min Act: -0.1700
Data Index: 1148333 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1317. Min Range: -8.1317
Max Act: 7.3192. Min Act: -0.1700
Data Index: 3214848 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1317. Min Range: -8.1317
Max Act: 7.3192. Min Act: -0.1700
Data Index: 8509838 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1317. Min Range: -8.1317
Max Act: 7.2879. Min Act: -0.1700
Data Index: 947742 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1317. Min Range: -8.1317
Max Act: 7.2879. Min Act: -0.1700
Data Index: 3787748 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1317. Min Range: -8.1317
Max Act: 7.2567. Min Act: -0.1700
Data Index: 6508622 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1317. Min Range: -8.1317
Max Act: 7.2254. Min Act: -0.1700
Data Index: 2457651 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1317. Min Range: -8.1317
Max Act: 7.2567. Min Act: -0.1700
Data Index: 755958 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1317. Min Range: -8.1317
Max Act: 7.2254. Min Act: -0.1700
Data Index: 7933884 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1317. Min Range: -8.1317
Max Act: 7.1942. Min Act: -0.1700
Data Index: 6297120 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1317. Min Range: -8.1317
Max Act: 7.1629. Min Act: -0.1700
Data Index: 8244754 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #19