Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2997 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6004. Min Range: -4.6004
Max Act: 4.6004. Min Act: -0.1700
Data Index: 7220132 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6004. Min Range: -4.6004
Max Act: 4.5692. Min Act: -0.1700
Data Index: 2287515 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6004. Min Range: -4.6004
Max Act: 4.5692. Min Act: -0.1700
Data Index: 7545266 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6004. Min Range: -4.6004
Max Act: 4.5379. Min Act: -0.1700
Data Index: 346030 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6004. Min Range: -4.6004
Max Act: 4.5379. Min Act: -0.1700
Data Index: 33421 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6004. Min Range: -4.6004
Max Act: 4.5067. Min Act: -0.1700
Data Index: 2244233 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6004. Min Range: -4.6004
Max Act: 4.5067. Min Act: -0.1700
Data Index: 1529900 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6004. Min Range: -4.6004
Max Act: 4.4754. Min Act: -0.1700
Data Index: 947518 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6004. Min Range: -4.6004
Max Act: 4.4754. Min Act: -0.1700
Data Index: 1475871 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6004. Min Range: -4.6004
Max Act: 4.4754. Min Act: -0.1700
Data Index: 5131680 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6004. Min Range: -4.6004
Max Act: 4.4442. Min Act: -0.1700
Data Index: 782961 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6004. Min Range: -4.6004
Max Act: 4.4442. Min Act: -0.1700
Data Index: 1364178 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6004. Min Range: -4.6004
Max Act: 4.4754. Min Act: -0.1700
Data Index: 4246625 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6004. Min Range: -4.6004
Max Act: 4.4442. Min Act: -0.1700
Data Index: 853119 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6004. Min Range: -4.6004
Max Act: 4.4129. Min Act: -0.1700
Data Index: 4198441 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6004. Min Range: -4.6004
Max Act: 4.4129. Min Act: -0.1700
Data Index: 4197122 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6004. Min Range: -4.6004
Max Act: 4.4129. Min Act: -0.1700
Data Index: 1941279 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6004. Min Range: -4.6004
Max Act: 4.4129. Min Act: -0.1700
Data Index: 6625192 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6004. Min Range: -4.6004
Max Act: 4.4129. Min Act: -0.1700
Data Index: 464394 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6004. Min Range: -4.6004
Max Act: 4.4129. Min Act: -0.1700
Data Index: 6700610 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #19