Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5090 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.9316. Min Range: -11.9316
Max Act: 11.9316. Min Act: -0.1700
Data Index: 5478626 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.9316. Min Range: -11.9316
Max Act: 11.8066. Min Act: -0.1700
Data Index: 508841 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.9316. Min Range: -11.9316
Max Act: 11.6191. Min Act: -0.1700
Data Index: 1658561 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.9316. Min Range: -11.9316
Max Act: 11.5566. Min Act: -0.1700
Data Index: 1610710 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.9316. Min Range: -11.9316
Max Act: 11.4941. Min Act: -0.1700
Data Index: 8096430 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.9316. Min Range: -11.9316
Max Act: 11.3691. Min Act: -0.1700
Data Index: 3373312 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.9316. Min Range: -11.9316
Max Act: 11.3066. Min Act: -0.1700
Data Index: 855617 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.9316. Min Range: -11.9316
Max Act: 11.2441. Min Act: -0.1700
Data Index: 3700475 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.9316. Min Range: -11.9316
Max Act: 11.2441. Min Act: -0.1700
Data Index: 4471025 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.9316. Min Range: -11.9316
Max Act: 11.1816. Min Act: -0.1700
Data Index: 7626094 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.9316. Min Range: -11.9316
Max Act: 11.1816. Min Act: -0.1700
Data Index: 7724183 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.9316. Min Range: -11.9316
Max Act: 11.1816. Min Act: -0.1700
Data Index: 3904711 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.9316. Min Range: -11.9316
Max Act: 11.1816. Min Act: -0.1700
Data Index: 6882159 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.9316. Min Range: -11.9316
Max Act: 11.1191. Min Act: -0.1700
Data Index: 6755035 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.9316. Min Range: -11.9316
Max Act: 11.1191. Min Act: -0.1700
Data Index: 5028814 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.9316. Min Range: -11.9316
Max Act: 11.1191. Min Act: -0.1700
Data Index: 739902 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.9316. Min Range: -11.9316
Max Act: 11.1191. Min Act: -0.1700
Data Index: 1476805 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.9316. Min Range: -11.9316
Max Act: 11.0566. Min Act: -0.1700
Data Index: 3413243 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.9316. Min Range: -11.9316
Max Act: 11.0566. Min Act: -0.1700
Data Index: 3061725 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.9316. Min Range: -11.9316
Max Act: 11.0566. Min Act: -0.1700
Data Index: 6975856 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #19