Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6364 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3168. Min Range: -6.3168
Max Act: 6.3168. Min Act: -0.1700
Data Index: 6372046 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3168. Min Range: -6.3168
Max Act: 6.2543. Min Act: -0.1700
Data Index: 8194608 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3168. Min Range: -6.3168
Max Act: 6.1293. Min Act: -0.1700
Data Index: 8298966 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3168. Min Range: -6.3168
Max Act: 6.0668. Min Act: -0.1700
Data Index: 5650396 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3168. Min Range: -6.3168
Max Act: 6.0355. Min Act: -0.1700
Data Index: 4547485 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3168. Min Range: -6.3168
Max Act: 6.0043. Min Act: -0.1700
Data Index: 466635 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3168. Min Range: -6.3168
Max Act: 6.0043. Min Act: -0.1700
Data Index: 4547490 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3168. Min Range: -6.3168
Max Act: 5.8793. Min Act: -0.1700
Data Index: 6788107 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3168. Min Range: -6.3168
Max Act: 5.8793. Min Act: -0.1700
Data Index: 891313 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3168. Min Range: -6.3168
Max Act: 5.8793. Min Act: -0.1700
Data Index: 4209621 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3168. Min Range: -6.3168
Max Act: 5.8480. Min Act: -0.1700
Data Index: 8569860 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3168. Min Range: -6.3168
Max Act: 5.8168. Min Act: -0.1700
Data Index: 7632102 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3168. Min Range: -6.3168
Max Act: 5.8480. Min Act: -0.1700
Data Index: 7235230 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3168. Min Range: -6.3168
Max Act: 5.8480. Min Act: -0.1700
Data Index: 5236780 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3168. Min Range: -6.3168
Max Act: 5.8168. Min Act: -0.1700
Data Index: 3931680 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3168. Min Range: -6.3168
Max Act: 5.8168. Min Act: -0.1700
Data Index: 6171295 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3168. Min Range: -6.3168
Max Act: 5.8168. Min Act: -0.1700
Data Index: 5503304 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3168. Min Range: -6.3168
Max Act: 5.8168. Min Act: -0.1700
Data Index: 1579788 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3168. Min Range: -6.3168
Max Act: 5.7855. Min Act: -0.1700
Data Index: 2454364 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3168. Min Range: -6.3168
Max Act: 5.7855. Min Act: -0.1700
Data Index: 5545490 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #19