Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3272 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9670. Min Range: -6.9670
Max Act: 6.9670. Min Act: -0.1700
Data Index: 2451186 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9670. Min Range: -6.9670
Max Act: 6.9045. Min Act: -0.1700
Data Index: 8370648 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9670. Min Range: -6.9670
Max Act: 6.9045. Min Act: -0.1700
Data Index: 7093016 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9670. Min Range: -6.9670
Max Act: 6.8107. Min Act: -0.1700
Data Index: 1397677 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9670. Min Range: -6.9670
Max Act: 6.7482. Min Act: -0.1700
Data Index: 8722358 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9670. Min Range: -6.9670
Max Act: 6.7482. Min Act: -0.1700
Data Index: 1162489 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9670. Min Range: -6.9670
Max Act: 6.7170. Min Act: -0.1700
Data Index: 4913565 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9670. Min Range: -6.9670
Max Act: 6.7170. Min Act: -0.1700
Data Index: 3933497 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9670. Min Range: -6.9670
Max Act: 6.6857. Min Act: -0.1700
Data Index: 4117077 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9670. Min Range: -6.9670
Max Act: 6.6545. Min Act: -0.1700
Data Index: 645957 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9670. Min Range: -6.9670
Max Act: 6.6545. Min Act: -0.1700
Data Index: 2310721 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9670. Min Range: -6.9670
Max Act: 6.6232. Min Act: -0.1700
Data Index: 2761154 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9670. Min Range: -6.9670
Max Act: 6.5920. Min Act: -0.1700
Data Index: 4393392 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9670. Min Range: -6.9670
Max Act: 6.5607. Min Act: -0.1700
Data Index: 6254093 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9670. Min Range: -6.9670
Max Act: 6.5607. Min Act: -0.1641
Data Index: 375723 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9670. Min Range: -6.9670
Max Act: 6.5295. Min Act: -0.1700
Data Index: 200468 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9670. Min Range: -6.9670
Max Act: 6.5295. Min Act: -0.1700
Data Index: 3589647 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9670. Min Range: -6.9670
Max Act: 6.5295. Min Act: -0.1700
Data Index: 4680969 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9670. Min Range: -6.9670
Max Act: 6.5295. Min Act: -0.1688
Data Index: 8141094 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9670. Min Range: -6.9670
Max Act: 6.5295. Min Act: -0.1699
Data Index: 6289892 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #19