Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1205 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2549. Min Range: -9.2549
Max Act: 9.2549. Min Act: -0.1700
Data Index: 543518 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2549. Min Range: -9.2549
Max Act: 9.0674. Min Act: -0.1700
Data Index: 8745603 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2549. Min Range: -9.2549
Max Act: 9.1299. Min Act: -0.1700
Data Index: 5945308 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2549. Min Range: -9.2549
Max Act: 9.0674. Min Act: -0.1700
Data Index: 7043500 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2549. Min Range: -9.2549
Max Act: 8.9424. Min Act: -0.1700
Data Index: 5922850 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2549. Min Range: -9.2549
Max Act: 8.9424. Min Act: -0.1700
Data Index: 7551524 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2549. Min Range: -9.2549
Max Act: 8.8799. Min Act: -0.1700
Data Index: 3770454 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2549. Min Range: -9.2549
Max Act: 8.8174. Min Act: -0.1700
Data Index: 2657561 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2549. Min Range: -9.2549
Max Act: 8.8174. Min Act: -0.1700
Data Index: 950618 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2549. Min Range: -9.2549
Max Act: 8.8174. Min Act: -0.1700
Data Index: 3144085 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2549. Min Range: -9.2549
Max Act: 8.7549. Min Act: -0.1700
Data Index: 4534624 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2549. Min Range: -9.2549
Max Act: 8.7549. Min Act: -0.1700
Data Index: 7456829 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2549. Min Range: -9.2549
Max Act: 8.7549. Min Act: -0.1700
Data Index: 5491066 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2549. Min Range: -9.2549
Max Act: 8.7549. Min Act: -0.1700
Data Index: 1667367 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2549. Min Range: -9.2549
Max Act: 8.6924. Min Act: -0.1700
Data Index: 4679589 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2549. Min Range: -9.2549
Max Act: 8.6924. Min Act: -0.1700
Data Index: 2379649 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2549. Min Range: -9.2549
Max Act: 8.6924. Min Act: -0.1700
Data Index: 2705955 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2549. Min Range: -9.2549
Max Act: 8.7549. Min Act: -0.1700
Data Index: 5039616 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2549. Min Range: -9.2549
Max Act: 8.6924. Min Act: -0.1700
Data Index: 5663876 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2549. Min Range: -9.2549
Max Act: 8.6924. Min Act: -0.1700
Data Index: 6601186 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #19