Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3500 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0325. Min Range: -5.0325
Max Act: 5.0325. Min Act: -0.1700
Data Index: 1761297 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0325. Min Range: -5.0325
Max Act: 5.0325. Min Act: -0.1700
Data Index: 1331948 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0325. Min Range: -5.0325
Max Act: 5.0012. Min Act: -0.1700
Data Index: 8408368 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0325. Min Range: -5.0325
Max Act: 5.0012. Min Act: -0.1700
Data Index: 5058196 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0325. Min Range: -5.0325
Max Act: 5.0325. Min Act: -0.1700
Data Index: 735537 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0325. Min Range: -5.0325
Max Act: 4.9387. Min Act: -0.1700
Data Index: 7588110 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0325. Min Range: -5.0325
Max Act: 4.9387. Min Act: -0.1700
Data Index: 338791 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0325. Min Range: -5.0325
Max Act: 4.9387. Min Act: -0.1700
Data Index: 6816437 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0325. Min Range: -5.0325
Max Act: 4.9075. Min Act: -0.1700
Data Index: 6098403 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0325. Min Range: -5.0325
Max Act: 4.9075. Min Act: -0.1700
Data Index: 1457877 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0325. Min Range: -5.0325
Max Act: 4.9387. Min Act: -0.1700
Data Index: 4070623 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0325. Min Range: -5.0325
Max Act: 4.8450. Min Act: -0.1700
Data Index: 7462449 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0325. Min Range: -5.0325
Max Act: 4.8762. Min Act: -0.1700
Data Index: 1218981 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0325. Min Range: -5.0325
Max Act: 4.8450. Min Act: -0.1700
Data Index: 1634511 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0325. Min Range: -5.0325
Max Act: 4.8450. Min Act: -0.1700
Data Index: 7400316 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0325. Min Range: -5.0325
Max Act: 4.8450. Min Act: -0.1700
Data Index: 4946014 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0325. Min Range: -5.0325
Max Act: 4.8450. Min Act: -0.1700
Data Index: 6513317 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0325. Min Range: -5.0325
Max Act: 4.8450. Min Act: -0.1700
Data Index: 6427970 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0325. Min Range: -5.0325
Max Act: 4.8137. Min Act: -0.1700
Data Index: 2063496 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0325. Min Range: -5.0325
Max Act: 4.8450. Min Act: -0.1700
Data Index: 3172590 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #19