Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2563 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.0240. Min Range: -1.0240
Max Act: 1.0240. Min Act: -0.1700
Data Index: 2252882 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.0240. Min Range: -1.0240
Max Act: 1.0240. Min Act: -0.1700
Data Index: 7373684 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.0240. Min Range: -1.0240
Max Act: 1.0153. Min Act: -0.1700
Data Index: 4121940 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.0240. Min Range: -1.0240
Max Act: 0.9806. Min Act: -0.1700
Data Index: 515066 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.0240. Min Range: -1.0240
Max Act: 0.9546. Min Act: -0.1700
Data Index: 4445079 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.0240. Min Range: -1.0240
Max Act: 0.9460. Min Act: -0.1700
Data Index: 4095589 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.0240. Min Range: -1.0240
Max Act: 0.9460. Min Act: -0.1700
Data Index: 2258086 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.0240. Min Range: -1.0240
Max Act: 0.9460. Min Act: -0.1700
Data Index: 5229922 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.0240. Min Range: -1.0240
Max Act: 0.9374. Min Act: -0.1700
Data Index: 6043165 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.0240. Min Range: -1.0240
Max Act: 0.9374. Min Act: -0.1700
Data Index: 7607884 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.0240. Min Range: -1.0240
Max Act: 0.9288. Min Act: -0.1700
Data Index: 3163958 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.0240. Min Range: -1.0240
Max Act: 0.9288. Min Act: -0.1700
Data Index: 3481575 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.0240. Min Range: -1.0240
Max Act: 0.9288. Min Act: -0.1700
Data Index: 5060752 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.0240. Min Range: -1.0240
Max Act: 0.9202. Min Act: -0.1700
Data Index: 7331958 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.0240. Min Range: -1.0240
Max Act: 0.9116. Min Act: -0.1700
Data Index: 1382693 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.0240. Min Range: -1.0240
Max Act: 0.9202. Min Act: -0.1700
Data Index: 7051418 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.0240. Min Range: -1.0240
Max Act: 0.9202. Min Act: -0.1700
Data Index: 4720336 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.0240. Min Range: -1.0240
Max Act: 0.9116. Min Act: -0.1700
Data Index: 7087256 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.0240. Min Range: -1.0240
Max Act: 0.9031. Min Act: -0.1700
Data Index: 2650160 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.0240. Min Range: -1.0240
Max Act: 0.9031. Min Act: -0.1700
Data Index: 2145025 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #19