Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4194 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7647. Min Range: -7.7647
Max Act: 7.7647. Min Act: -0.1700
Data Index: 48911 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7647. Min Range: -7.7647
Max Act: 7.7022. Min Act: -0.1700
Data Index: 6778522 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7647. Min Range: -7.7647
Max Act: 7.5772. Min Act: -0.1700
Data Index: 6173562 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7647. Min Range: -7.7647
Max Act: 7.5460. Min Act: -0.1700
Data Index: 284791 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7647. Min Range: -7.7647
Max Act: 7.5460. Min Act: -0.1700
Data Index: 3074172 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7647. Min Range: -7.7647
Max Act: 7.5460. Min Act: -0.1700
Data Index: 2975095 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7647. Min Range: -7.7647
Max Act: 7.5147. Min Act: -0.1700
Data Index: 8248785 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7647. Min Range: -7.7647
Max Act: 7.4835. Min Act: -0.1700
Data Index: 1042201 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7647. Min Range: -7.7647
Max Act: 7.4210. Min Act: -0.1700
Data Index: 1961185 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7647. Min Range: -7.7647
Max Act: 7.4210. Min Act: -0.1700
Data Index: 6169230 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7647. Min Range: -7.7647
Max Act: 7.4210. Min Act: -0.1700
Data Index: 6857765 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7647. Min Range: -7.7647
Max Act: 7.3897. Min Act: -0.1700
Data Index: 3984539 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7647. Min Range: -7.7647
Max Act: 7.3897. Min Act: -0.1700
Data Index: 6138544 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7647. Min Range: -7.7647
Max Act: 7.3272. Min Act: -0.1700
Data Index: 5286369 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7647. Min Range: -7.7647
Max Act: 7.3272. Min Act: -0.1700
Data Index: 4907151 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7647. Min Range: -7.7647
Max Act: 7.3272. Min Act: -0.1700
Data Index: 3892327 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7647. Min Range: -7.7647
Max Act: 7.2647. Min Act: -0.1700
Data Index: 5522324 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7647. Min Range: -7.7647
Max Act: 7.2960. Min Act: -0.1700
Data Index: 706027 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7647. Min Range: -7.7647
Max Act: 7.2022. Min Act: -0.1700
Data Index: 7277925 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7647. Min Range: -7.7647
Max Act: 7.2335. Min Act: -0.1700
Data Index: 4858575 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #19