Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3447 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4685. Min Range: -8.4685
Max Act: 8.4685. Min Act: -0.1700
Data Index: 6173873 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4685. Min Range: -8.4685
Max Act: 8.3123. Min Act: -0.1700
Data Index: 5328634 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4685. Min Range: -8.4685
Max Act: 8.0623. Min Act: -0.1700
Data Index: 3405948 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4685. Min Range: -8.4685
Max Act: 7.9685. Min Act: -0.1700
Data Index: 753250 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4685. Min Range: -8.4685
Max Act: 7.9373. Min Act: -0.1700
Data Index: 4094471 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4685. Min Range: -8.4685
Max Act: 7.6873. Min Act: -0.1700
Data Index: 4963487 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4685. Min Range: -8.4685
Max Act: 7.6560. Min Act: -0.1700
Data Index: 2921040 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4685. Min Range: -8.4685
Max Act: 7.6560. Min Act: -0.1700
Data Index: 7969997 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4685. Min Range: -8.4685
Max Act: 7.6248. Min Act: -0.1700
Data Index: 8203669 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4685. Min Range: -8.4685
Max Act: 7.6248. Min Act: -0.1700
Data Index: 8758216 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4685. Min Range: -8.4685
Max Act: 7.5623. Min Act: -0.1700
Data Index: 4731342 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4685. Min Range: -8.4685
Max Act: 7.5623. Min Act: -0.1700
Data Index: 3419352 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4685. Min Range: -8.4685
Max Act: 7.5623. Min Act: -0.1700
Data Index: 1518573 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4685. Min Range: -8.4685
Max Act: 7.5310. Min Act: -0.1700
Data Index: 5999050 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4685. Min Range: -8.4685
Max Act: 7.4998. Min Act: -0.1700
Data Index: 5620372 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4685. Min Range: -8.4685
Max Act: 7.4998. Min Act: -0.1700
Data Index: 7201598 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4685. Min Range: -8.4685
Max Act: 7.4998. Min Act: -0.1700
Data Index: 3822068 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4685. Min Range: -8.4685
Max Act: 7.4998. Min Act: -0.1700
Data Index: 7100450 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4685. Min Range: -8.4685
Max Act: 7.4373. Min Act: -0.1700
Data Index: 6376193 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4685. Min Range: -8.4685
Max Act: 7.4060. Min Act: -0.1700
Data Index: 6712784 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #19