Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2089 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5161. Min Range: -4.5161
Max Act: 4.5161. Min Act: -0.1700
Data Index: 4638429 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5161. Min Range: -4.5161
Max Act: 4.2974. Min Act: -0.1700
Data Index: 279110 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5161. Min Range: -4.5161
Max Act: 4.2661. Min Act: -0.1700
Data Index: 1834107 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5161. Min Range: -4.5161
Max Act: 4.2349. Min Act: -0.1700
Data Index: 7120782 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5161. Min Range: -4.5161
Max Act: 4.2349. Min Act: -0.1700
Data Index: 7885109 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5161. Min Range: -4.5161
Max Act: 4.2036. Min Act: -0.1700
Data Index: 2153126 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5161. Min Range: -4.5161
Max Act: 4.1724. Min Act: -0.1700
Data Index: 5616 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5161. Min Range: -4.5161
Max Act: 4.1411. Min Act: -0.1700
Data Index: 2922600 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5161. Min Range: -4.5161
Max Act: 4.1099. Min Act: -0.1700
Data Index: 3557900 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5161. Min Range: -4.5161
Max Act: 4.1099. Min Act: -0.1700
Data Index: 8263155 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5161. Min Range: -4.5161
Max Act: 4.1411. Min Act: -0.1700
Data Index: 6935838 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5161. Min Range: -4.5161
Max Act: 4.1099. Min Act: -0.1700
Data Index: 8191831 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5161. Min Range: -4.5161
Max Act: 4.1099. Min Act: -0.1700
Data Index: 8212098 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5161. Min Range: -4.5161
Max Act: 4.0786. Min Act: -0.1700
Data Index: 785615 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5161. Min Range: -4.5161
Max Act: 4.0786. Min Act: -0.1700
Data Index: 3769140 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5161. Min Range: -4.5161
Max Act: 4.0786. Min Act: -0.1700
Data Index: 7387748 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5161. Min Range: -4.5161
Max Act: 4.0786. Min Act: -0.1700
Data Index: 2110706 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5161. Min Range: -4.5161
Max Act: 4.0473. Min Act: -0.1700
Data Index: 8401614 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5161. Min Range: -4.5161
Max Act: 4.0786. Min Act: -0.1700
Data Index: 7820192 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5161. Min Range: -4.5161
Max Act: 4.0473. Min Act: -0.1700
Data Index: 7745939 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #19