Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3016 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9088. Min Range: -3.9088
Max Act: 3.9088. Min Act: -0.1700
Data Index: 7141704 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9088. Min Range: -3.9088
Max Act: 3.8931. Min Act: -0.1700
Data Index: 7513567 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9088. Min Range: -3.9088
Max Act: 3.8775. Min Act: -0.1700
Data Index: 4816833 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9088. Min Range: -3.9088
Max Act: 3.8931. Min Act: -0.1700
Data Index: 4465261 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9088. Min Range: -3.9088
Max Act: 3.8462. Min Act: -0.1700
Data Index: 4007755 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9088. Min Range: -3.9088
Max Act: 3.8462. Min Act: -0.1700
Data Index: 1641744 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9088. Min Range: -3.9088
Max Act: 3.8306. Min Act: -0.1700
Data Index: 5938730 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9088. Min Range: -3.9088
Max Act: 3.8306. Min Act: -0.1700
Data Index: 3132689 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9088. Min Range: -3.9088
Max Act: 3.8150. Min Act: -0.1700
Data Index: 5186715 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9088. Min Range: -3.9088
Max Act: 3.7993. Min Act: -0.1700
Data Index: 1729070 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9088. Min Range: -3.9088
Max Act: 3.7993. Min Act: -0.1700
Data Index: 5079857 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9088. Min Range: -3.9088
Max Act: 3.7993. Min Act: -0.1700
Data Index: 528288 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9088. Min Range: -3.9088
Max Act: 3.7837. Min Act: -0.1700
Data Index: 3400557 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9088. Min Range: -3.9088
Max Act: 3.7837. Min Act: -0.1700
Data Index: 4369949 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9088. Min Range: -3.9088
Max Act: 3.7681. Min Act: -0.1700
Data Index: 3875402 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9088. Min Range: -3.9088
Max Act: 3.7681. Min Act: -0.1700
Data Index: 600683 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9088. Min Range: -3.9088
Max Act: 3.7681. Min Act: -0.1700
Data Index: 8179794 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9088. Min Range: -3.9088
Max Act: 3.7368. Min Act: -0.1700
Data Index: 7470459 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9088. Min Range: -3.9088
Max Act: 3.7524. Min Act: -0.1700
Data Index: 6160337 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9088. Min Range: -3.9088
Max Act: 3.7524. Min Act: -0.1700
Data Index: 5834714 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #19