Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3749 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7422. Min Range: -5.7422
Max Act: 5.7422. Min Act: -0.1700
Data Index: 2110752 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7422. Min Range: -5.7422
Max Act: 5.2422. Min Act: -0.1700
Data Index: 8109273 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7422. Min Range: -5.7422
Max Act: 5.1797. Min Act: -0.1700
Data Index: 6083845 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7422. Min Range: -5.7422
Max Act: 5.1797. Min Act: -0.1700
Data Index: 2985939 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7422. Min Range: -5.7422
Max Act: 5.1797. Min Act: -0.1700
Data Index: 4389191 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7422. Min Range: -5.7422
Max Act: 5.1485. Min Act: -0.1700
Data Index: 5075465 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7422. Min Range: -5.7422
Max Act: 5.0860. Min Act: -0.1700
Data Index: 7320118 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7422. Min Range: -5.7422
Max Act: 5.0547. Min Act: -0.1700
Data Index: 3288660 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7422. Min Range: -5.7422
Max Act: 5.0547. Min Act: -0.1700
Data Index: 3424658 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7422. Min Range: -5.7422
Max Act: 5.0235. Min Act: -0.1700
Data Index: 6109354 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7422. Min Range: -5.7422
Max Act: 5.0235. Min Act: -0.1700
Data Index: 225030 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7422. Min Range: -5.7422
Max Act: 4.9922. Min Act: -0.1700
Data Index: 4732200 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7422. Min Range: -5.7422
Max Act: 4.9610. Min Act: -0.1700
Data Index: 8517807 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7422. Min Range: -5.7422
Max Act: 4.9922. Min Act: -0.1700
Data Index: 1491062 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7422. Min Range: -5.7422
Max Act: 4.9610. Min Act: -0.1700
Data Index: 122019 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7422. Min Range: -5.7422
Max Act: 4.9297. Min Act: -0.1700
Data Index: 2959802 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7422. Min Range: -5.7422
Max Act: 4.9297. Min Act: -0.1700
Data Index: 1327413 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7422. Min Range: -5.7422
Max Act: 4.8985. Min Act: -0.1700
Data Index: 8410315 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7422. Min Range: -5.7422
Max Act: 4.9297. Min Act: -0.1700
Data Index: 5166268 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7422. Min Range: -5.7422
Max Act: 4.8985. Min Act: -0.1700
Data Index: 3118193 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #19