Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4401 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3487. Min Range: -7.3487
Max Act: 7.3487. Min Act: -0.1700
Data Index: 4633624 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3487. Min Range: -7.3487
Max Act: 7.2550. Min Act: -0.1700
Data Index: 5002026 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3487. Min Range: -7.3487
Max Act: 7.1612. Min Act: -0.1700
Data Index: 7388503 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3487. Min Range: -7.3487
Max Act: 7.1612. Min Act: -0.1700
Data Index: 5759834 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3487. Min Range: -7.3487
Max Act: 7.1300. Min Act: -0.1700
Data Index: 86607 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3487. Min Range: -7.3487
Max Act: 7.0362. Min Act: -0.1700
Data Index: 8783965 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3487. Min Range: -7.3487
Max Act: 7.0362. Min Act: -0.1700
Data Index: 2353704 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3487. Min Range: -7.3487
Max Act: 7.0362. Min Act: -0.1700
Data Index: 3892490 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3487. Min Range: -7.3487
Max Act: 6.9737. Min Act: -0.1700
Data Index: 8807747 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3487. Min Range: -7.3487
Max Act: 7.0050. Min Act: -0.1700
Data Index: 8383321 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3487. Min Range: -7.3487
Max Act: 6.9112. Min Act: -0.1700
Data Index: 7073343 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3487. Min Range: -7.3487
Max Act: 6.8800. Min Act: -0.1700
Data Index: 5780480 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3487. Min Range: -7.3487
Max Act: 6.8800. Min Act: -0.1700
Data Index: 7919306 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3487. Min Range: -7.3487
Max Act: 6.9112. Min Act: -0.1700
Data Index: 2614817 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3487. Min Range: -7.3487
Max Act: 6.8487. Min Act: -0.1700
Data Index: 1356305 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3487. Min Range: -7.3487
Max Act: 6.8175. Min Act: -0.1700
Data Index: 828173 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3487. Min Range: -7.3487
Max Act: 6.8175. Min Act: -0.1700
Data Index: 8155623 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3487. Min Range: -7.3487
Max Act: 6.7550. Min Act: -0.1700
Data Index: 6509519 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3487. Min Range: -7.3487
Max Act: 6.7550. Min Act: -0.1700
Data Index: 5565286 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3487. Min Range: -7.3487
Max Act: 6.7550. Min Act: -0.1700
Data Index: 6574626 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #19