Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3122 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4695. Min Range: -4.4695
Max Act: 4.4695. Min Act: -0.1700
Data Index: 7666804 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4695. Min Range: -4.4695
Max Act: 4.4070. Min Act: -0.1700
Data Index: 5123085 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4695. Min Range: -4.4695
Max Act: 4.2507. Min Act: -0.1700
Data Index: 1383057 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4695. Min Range: -4.4695
Max Act: 4.2507. Min Act: -0.1700
Data Index: 5109280 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4695. Min Range: -4.4695
Max Act: 4.2194. Min Act: -0.1700
Data Index: 3229668 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4695. Min Range: -4.4695
Max Act: 4.1569. Min Act: -0.1700
Data Index: 1438481 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4695. Min Range: -4.4695
Max Act: 4.1569. Min Act: -0.1700
Data Index: 7160814 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4695. Min Range: -4.4695
Max Act: 4.0944. Min Act: -0.1700
Data Index: 1481808 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4695. Min Range: -4.4695
Max Act: 4.0632. Min Act: -0.1700
Data Index: 7155952 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4695. Min Range: -4.4695
Max Act: 4.0319. Min Act: -0.1700
Data Index: 2562751 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4695. Min Range: -4.4695
Max Act: 4.0319. Min Act: -0.1700
Data Index: 2174102 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4695. Min Range: -4.4695
Max Act: 4.0319. Min Act: -0.1700
Data Index: 186801 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4695. Min Range: -4.4695
Max Act: 4.0006. Min Act: -0.1700
Data Index: 6050613 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4695. Min Range: -4.4695
Max Act: 4.0319. Min Act: -0.1700
Data Index: 5920259 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4695. Min Range: -4.4695
Max Act: 4.0319. Min Act: -0.1700
Data Index: 644493 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4695. Min Range: -4.4695
Max Act: 4.0006. Min Act: -0.1700
Data Index: 396984 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4695. Min Range: -4.4695
Max Act: 3.9694. Min Act: -0.1700
Data Index: 3633902 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4695. Min Range: -4.4695
Max Act: 4.0006. Min Act: -0.1700
Data Index: 3546084 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4695. Min Range: -4.4695
Max Act: 3.9381. Min Act: -0.1700
Data Index: 3613173 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4695. Min Range: -4.4695
Max Act: 3.9694. Min Act: -0.1700
Data Index: 3526618 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #19