Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2394 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.8189. Min Range: -2.8189
Max Act: 2.8189. Min Act: -0.1699
Data Index: 5987957 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8189. Min Range: -2.8189
Max Act: 2.7711. Min Act: -0.1700
Data Index: 5987990 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8189. Min Range: -2.8189
Max Act: 2.7552. Min Act: -0.1700
Data Index: 2456312 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8189. Min Range: -2.8189
Max Act: 2.7711. Min Act: -0.1700
Data Index: 5987978 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8189. Min Range: -2.8189
Max Act: 2.7552. Min Act: -0.1700
Data Index: 5988002 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8189. Min Range: -2.8189
Max Act: 2.7392. Min Act: -0.1700
Data Index: 4748689 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8189. Min Range: -2.8189
Max Act: 2.7392. Min Act: -0.1700
Data Index: 1247700 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8189. Min Range: -2.8189
Max Act: 2.7232. Min Act: -0.1700
Data Index: 3023275 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8189. Min Range: -2.8189
Max Act: 2.7232. Min Act: -0.1700
Data Index: 5987973 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8189. Min Range: -2.8189
Max Act: 2.7072. Min Act: -0.1700
Data Index: 2677053 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8189. Min Range: -2.8189
Max Act: 2.6912. Min Act: -0.1700
Data Index: 7598598 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8189. Min Range: -2.8189
Max Act: 2.6912. Min Act: -0.1700
Data Index: 1236349 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8189. Min Range: -2.8189
Max Act: 2.6912. Min Act: -0.1700
Data Index: 149750 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8189. Min Range: -2.8189
Max Act: 2.6752. Min Act: -0.1700
Data Index: 2962701 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8189. Min Range: -2.8189
Max Act: 2.6592. Min Act: -0.1700
Data Index: 4457091 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8189. Min Range: -2.8189
Max Act: 2.6752. Min Act: -0.1700
Data Index: 2171055 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8189. Min Range: -2.8189
Max Act: 2.6431. Min Act: -0.1700
Data Index: 5329732 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8189. Min Range: -2.8189
Max Act: 2.6271. Min Act: -0.1700
Data Index: 6501552 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8189. Min Range: -2.8189
Max Act: 2.6271. Min Act: -0.1700
Data Index: 5987956 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8189. Min Range: -2.8189
Max Act: 2.6271. Min Act: -0.1700
Data Index: 6694103 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #19