Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2063 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4671. Min Range: -6.4671
Max Act: 6.4671. Min Act: -0.1700
Data Index: 6909891 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4671. Min Range: -6.4671
Max Act: 6.1546. Min Act: -0.1700
Data Index: 1282064 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4671. Min Range: -6.4671
Max Act: 6.1233. Min Act: -0.1700
Data Index: 1245283 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4671. Min Range: -6.4671
Max Act: 6.1233. Min Act: -0.1700
Data Index: 1754413 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4671. Min Range: -6.4671
Max Act: 6.0921. Min Act: -0.1700
Data Index: 4341222 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4671. Min Range: -6.4671
Max Act: 6.0921. Min Act: -0.1700
Data Index: 6606104 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4671. Min Range: -6.4671
Max Act: 6.0608. Min Act: -0.1700
Data Index: 4041781 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4671. Min Range: -6.4671
Max Act: 6.0608. Min Act: -0.1700
Data Index: 6399572 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4671. Min Range: -6.4671
Max Act: 6.0608. Min Act: -0.1700
Data Index: 593429 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4671. Min Range: -6.4671
Max Act: 6.0296. Min Act: -0.1700
Data Index: 3938204 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4671. Min Range: -6.4671
Max Act: 5.9983. Min Act: -0.1699
Data Index: 4936322 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4671. Min Range: -6.4671
Max Act: 5.9671. Min Act: -0.1700
Data Index: 7321431 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4671. Min Range: -6.4671
Max Act: 5.9671. Min Act: -0.1700
Data Index: 3145873 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4671. Min Range: -6.4671
Max Act: 5.9671. Min Act: -0.1700
Data Index: 7640083 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4671. Min Range: -6.4671
Max Act: 5.9671. Min Act: -0.1700
Data Index: 8655402 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4671. Min Range: -6.4671
Max Act: 5.9671. Min Act: -0.1700
Data Index: 6726508 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4671. Min Range: -6.4671
Max Act: 5.9671. Min Act: -0.1700
Data Index: 1245284 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4671. Min Range: -6.4671
Max Act: 5.9358. Min Act: -0.1700
Data Index: 4906019 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4671. Min Range: -6.4671
Max Act: 5.9671. Min Act: -0.1700
Data Index: 349121 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4671. Min Range: -6.4671
Max Act: 5.9358. Min Act: -0.1700
Data Index: 3462330 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #19