Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2846 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0824. Min Range: -6.0824
Max Act: 6.0824. Min Act: -0.1700
Data Index: 4353803 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0824. Min Range: -6.0824
Max Act: 6.0199. Min Act: -0.1700
Data Index: 653558 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0824. Min Range: -6.0824
Max Act: 6.0199. Min Act: -0.1700
Data Index: 1974809 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0824. Min Range: -6.0824
Max Act: 5.9262. Min Act: -0.1700
Data Index: 743028 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0824. Min Range: -6.0824
Max Act: 5.9262. Min Act: -0.1700
Data Index: 6146580 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0824. Min Range: -6.0824
Max Act: 5.8949. Min Act: -0.1699
Data Index: 6054351 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0824. Min Range: -6.0824
Max Act: 5.8637. Min Act: -0.1700
Data Index: 6041066 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0824. Min Range: -6.0824
Max Act: 5.8637. Min Act: -0.1700
Data Index: 4139002 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0824. Min Range: -6.0824
Max Act: 5.8324. Min Act: -0.1700
Data Index: 7331916 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0824. Min Range: -6.0824
Max Act: 5.8324. Min Act: -0.1700
Data Index: 8816486 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0824. Min Range: -6.0824
Max Act: 5.8012. Min Act: -0.1700
Data Index: 3532540 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0824. Min Range: -6.0824
Max Act: 5.8012. Min Act: -0.1700
Data Index: 296056 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0824. Min Range: -6.0824
Max Act: 5.8012. Min Act: -0.1700
Data Index: 3454321 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0824. Min Range: -6.0824
Max Act: 5.8012. Min Act: -0.1700
Data Index: 3418607 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0824. Min Range: -6.0824
Max Act: 5.8012. Min Act: -0.1700
Data Index: 7453655 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0824. Min Range: -6.0824
Max Act: 5.8012. Min Act: -0.1700
Data Index: 3221881 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0824. Min Range: -6.0824
Max Act: 5.7699. Min Act: -0.1700
Data Index: 6305653 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0824. Min Range: -6.0824
Max Act: 5.7699. Min Act: -0.1700
Data Index: 5915466 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0824. Min Range: -6.0824
Max Act: 5.7699. Min Act: -0.1700
Data Index: 5773600 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0824. Min Range: -6.0824
Max Act: 5.7699. Min Act: -0.1700
Data Index: 4521589 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #19