Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1955 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0532. Min Range: -7.0532
Max Act: 7.0532. Min Act: -0.1700
Data Index: 8307046 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0532. Min Range: -7.0532
Max Act: 6.8032. Min Act: -0.1700
Data Index: 6003359 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0532. Min Range: -7.0532
Max Act: 6.6469. Min Act: -0.1700
Data Index: 842999 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0532. Min Range: -7.0532
Max Act: 6.6157. Min Act: -0.1700
Data Index: 4184808 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0532. Min Range: -7.0532
Max Act: 6.5532. Min Act: -0.1700
Data Index: 8718163 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0532. Min Range: -7.0532
Max Act: 6.5532. Min Act: -0.1700
Data Index: 29600 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0532. Min Range: -7.0532
Max Act: 6.5219. Min Act: -0.1700
Data Index: 7723938 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0532. Min Range: -7.0532
Max Act: 6.5219. Min Act: -0.1700
Data Index: 4598268 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0532. Min Range: -7.0532
Max Act: 6.5219. Min Act: -0.1700
Data Index: 3466325 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0532. Min Range: -7.0532
Max Act: 6.4907. Min Act: -0.1700
Data Index: 2277634 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0532. Min Range: -7.0532
Max Act: 6.4907. Min Act: -0.1700
Data Index: 1503723 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0532. Min Range: -7.0532
Max Act: 6.4907. Min Act: -0.1700
Data Index: 1053672 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0532. Min Range: -7.0532
Max Act: 6.4594. Min Act: -0.1700
Data Index: 6990784 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0532. Min Range: -7.0532
Max Act: 6.4594. Min Act: -0.1700
Data Index: 3648264 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0532. Min Range: -7.0532
Max Act: 6.4594. Min Act: -0.1700
Data Index: 1927268 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0532. Min Range: -7.0532
Max Act: 6.4282. Min Act: -0.1700
Data Index: 40502 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0532. Min Range: -7.0532
Max Act: 6.4282. Min Act: -0.1700
Data Index: 4273068 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0532. Min Range: -7.0532
Max Act: 6.3969. Min Act: -0.1700
Data Index: 522433 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0532. Min Range: -7.0532
Max Act: 6.3969. Min Act: -0.1700
Data Index: 3662352 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0532. Min Range: -7.0532
Max Act: 6.3969. Min Act: -0.1700
Data Index: 4437999 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #19