Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1510 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7484. Min Range: -5.7484
Max Act: 5.7484. Min Act: -0.1700
Data Index: 126682 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7484. Min Range: -5.7484
Max Act: 5.2797. Min Act: -0.1700
Data Index: 7255235 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7484. Min Range: -5.7484
Max Act: 5.2172. Min Act: -0.1700
Data Index: 1702601 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7484. Min Range: -5.7484
Max Act: 5.2484. Min Act: -0.1700
Data Index: 3445467 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7484. Min Range: -5.7484
Max Act: 5.2484. Min Act: -0.1700
Data Index: 8031544 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7484. Min Range: -5.7484
Max Act: 5.2484. Min Act: -0.1700
Data Index: 3274144 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7484. Min Range: -5.7484
Max Act: 5.2172. Min Act: -0.1700
Data Index: 8476107 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7484. Min Range: -5.7484
Max Act: 5.1859. Min Act: -0.1700
Data Index: 5855749 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7484. Min Range: -5.7484
Max Act: 5.1547. Min Act: -0.1700
Data Index: 3539429 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7484. Min Range: -5.7484
Max Act: 5.1859. Min Act: -0.1700
Data Index: 8826392 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7484. Min Range: -5.7484
Max Act: 5.1547. Min Act: -0.1700
Data Index: 6342992 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7484. Min Range: -5.7484
Max Act: 5.1859. Min Act: -0.1700
Data Index: 8258841 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7484. Min Range: -5.7484
Max Act: 5.1859. Min Act: -0.1700
Data Index: 2959348 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7484. Min Range: -5.7484
Max Act: 5.1547. Min Act: -0.1700
Data Index: 1810720 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7484. Min Range: -5.7484
Max Act: 5.1234. Min Act: -0.1700
Data Index: 1490343 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7484. Min Range: -5.7484
Max Act: 5.1859. Min Act: -0.1700
Data Index: 6168051 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7484. Min Range: -5.7484
Max Act: 5.1547. Min Act: -0.1700
Data Index: 6421400 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7484. Min Range: -5.7484
Max Act: 5.1547. Min Act: -0.1700
Data Index: 5092433 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7484. Min Range: -5.7484
Max Act: 5.1547. Min Act: -0.1700
Data Index: 3660262 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7484. Min Range: -5.7484
Max Act: 5.1547. Min Act: -0.1700
Data Index: 3714179 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #19