Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2257 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0948. Min Range: -7.0948
Max Act: 7.0948. Min Act: -0.1700
Data Index: 6694038 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0948. Min Range: -7.0948
Max Act: 6.7198. Min Act: -0.1700
Data Index: 5910363 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0948. Min Range: -7.0948
Max Act: 6.6573. Min Act: -0.1700
Data Index: 2368321 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0948. Min Range: -7.0948
Max Act: 6.6573. Min Act: -0.1700
Data Index: 155320 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0948. Min Range: -7.0948
Max Act: 6.6261. Min Act: -0.1700
Data Index: 4881411 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0948. Min Range: -7.0948
Max Act: 6.6261. Min Act: -0.1700
Data Index: 6307556 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0948. Min Range: -7.0948
Max Act: 6.5948. Min Act: -0.1700
Data Index: 6841346 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0948. Min Range: -7.0948
Max Act: 6.5323. Min Act: -0.1700
Data Index: 553350 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0948. Min Range: -7.0948
Max Act: 6.5948. Min Act: -0.1700
Data Index: 3149193 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0948. Min Range: -7.0948
Max Act: 6.5636. Min Act: -0.1700
Data Index: 2246314 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0948. Min Range: -7.0948
Max Act: 6.5011. Min Act: -0.1700
Data Index: 412389 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0948. Min Range: -7.0948
Max Act: 6.4386. Min Act: -0.1700
Data Index: 411040 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0948. Min Range: -7.0948
Max Act: 6.3761. Min Act: -0.1700
Data Index: 4258827 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0948. Min Range: -7.0948
Max Act: 6.3761. Min Act: -0.1700
Data Index: 6152133 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0948. Min Range: -7.0948
Max Act: 6.3448. Min Act: -0.1700
Data Index: 3268084 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0948. Min Range: -7.0948
Max Act: 6.3136. Min Act: -0.1700
Data Index: 4466168 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0948. Min Range: -7.0948
Max Act: 6.3136. Min Act: -0.1700
Data Index: 2318130 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0948. Min Range: -7.0948
Max Act: 6.3136. Min Act: -0.1700
Data Index: 6194692 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0948. Min Range: -7.0948
Max Act: 6.2823. Min Act: -0.1700
Data Index: 316485 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0948. Min Range: -7.0948
Max Act: 6.2511. Min Act: -0.1700
Data Index: 5558851 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #19