Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4064 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9239. Min Range: -5.9239
Max Act: 5.9239. Min Act: -0.1700
Data Index: 1894007 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9239. Min Range: -5.9239
Max Act: 5.8614. Min Act: -0.1700
Data Index: 6465143 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9239. Min Range: -5.9239
Max Act: 5.8301. Min Act: -0.1700
Data Index: 3486053 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9239. Min Range: -5.9239
Max Act: 5.7989. Min Act: -0.1700
Data Index: 7077623 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9239. Min Range: -5.9239
Max Act: 5.7989. Min Act: -0.1700
Data Index: 8316925 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9239. Min Range: -5.9239
Max Act: 5.7676. Min Act: -0.1700
Data Index: 3070702 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9239. Min Range: -5.9239
Max Act: 5.7989. Min Act: -0.1700
Data Index: 5567958 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9239. Min Range: -5.9239
Max Act: 5.7676. Min Act: -0.1700
Data Index: 964054 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9239. Min Range: -5.9239
Max Act: 5.7676. Min Act: -0.1700
Data Index: 8244280 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9239. Min Range: -5.9239
Max Act: 5.7364. Min Act: -0.1700
Data Index: 3125319 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9239. Min Range: -5.9239
Max Act: 5.7364. Min Act: -0.1700
Data Index: 3668394 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9239. Min Range: -5.9239
Max Act: 5.7364. Min Act: -0.1700
Data Index: 4754038 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9239. Min Range: -5.9239
Max Act: 5.7364. Min Act: -0.1700
Data Index: 3399057 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9239. Min Range: -5.9239
Max Act: 5.7364. Min Act: -0.1700
Data Index: 757617 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9239. Min Range: -5.9239
Max Act: 5.7364. Min Act: -0.1700
Data Index: 3208090 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9239. Min Range: -5.9239
Max Act: 5.7051. Min Act: -0.1700
Data Index: 5858751 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9239. Min Range: -5.9239
Max Act: 5.7051. Min Act: -0.1700
Data Index: 2246408 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9239. Min Range: -5.9239
Max Act: 5.7051. Min Act: -0.1700
Data Index: 4255342 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9239. Min Range: -5.9239
Max Act: 5.7051. Min Act: -0.1700
Data Index: 2545172 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9239. Min Range: -5.9239
Max Act: 5.7364. Min Act: -0.1700
Data Index: 386005 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #19