Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1816 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2932. Min Range: -5.2932
Max Act: 5.2932. Min Act: -0.1700
Data Index: 3300213 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2932. Min Range: -5.2932
Max Act: 5.1994. Min Act: -0.1700
Data Index: 1707779 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2932. Min Range: -5.2932
Max Act: 5.1682. Min Act: -0.1700
Data Index: 7890515 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2932. Min Range: -5.2932
Max Act: 5.1682. Min Act: -0.1700
Data Index: 7393464 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2932. Min Range: -5.2932
Max Act: 5.1057. Min Act: -0.1700
Data Index: 3782101 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2932. Min Range: -5.2932
Max Act: 5.0744. Min Act: -0.1700
Data Index: 1026211 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2932. Min Range: -5.2932
Max Act: 5.0119. Min Act: -0.1700
Data Index: 1635640 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2932. Min Range: -5.2932
Max Act: 4.9807. Min Act: -0.1700
Data Index: 7604804 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2932. Min Range: -5.2932
Max Act: 4.9807. Min Act: -0.1700
Data Index: 491455 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2932. Min Range: -5.2932
Max Act: 4.9807. Min Act: -0.1700
Data Index: 5270682 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2932. Min Range: -5.2932
Max Act: 4.9807. Min Act: -0.1700
Data Index: 5270681 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2932. Min Range: -5.2932
Max Act: 4.9182. Min Act: -0.1700
Data Index: 5411747 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2932. Min Range: -5.2932
Max Act: 4.9182. Min Act: -0.1700
Data Index: 6560476 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2932. Min Range: -5.2932
Max Act: 4.8557. Min Act: -0.1700
Data Index: 7716364 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2932. Min Range: -5.2932
Max Act: 4.8557. Min Act: -0.1700
Data Index: 7906602 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2932. Min Range: -5.2932
Max Act: 4.8869. Min Act: -0.1700
Data Index: 7690085 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2932. Min Range: -5.2932
Max Act: 4.6994. Min Act: -0.1700
Data Index: 7600277 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2932. Min Range: -5.2932
Max Act: 4.6994. Min Act: -0.1700
Data Index: 3940001 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2932. Min Range: -5.2932
Max Act: 4.6369. Min Act: -0.1700
Data Index: 3753046 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2932. Min Range: -5.2932
Max Act: 4.6057. Min Act: -0.1700
Data Index: 7090298 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #19