Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2809 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.4443. Min Range: -2.4443
Max Act: 2.4443. Min Act: -0.1700
Data Index: 8004320 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4443. Min Range: -2.4443
Max Act: 2.3790. Min Act: -0.1700
Data Index: 1955859 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4443. Min Range: -2.4443
Max Act: 2.3627. Min Act: -0.1700
Data Index: 6427025 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4443. Min Range: -2.4443
Max Act: 2.3463. Min Act: -0.1700
Data Index: 2205920 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4443. Min Range: -2.4443
Max Act: 2.3135. Min Act: -0.1700
Data Index: 2377614 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4443. Min Range: -2.4443
Max Act: 2.3135. Min Act: -0.1700
Data Index: 5560304 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4443. Min Range: -2.4443
Max Act: 2.3135. Min Act: -0.1700
Data Index: 6142629 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4443. Min Range: -2.4443
Max Act: 2.2970. Min Act: -0.1700
Data Index: 6246972 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4443. Min Range: -2.4443
Max Act: 2.2970. Min Act: -0.1700
Data Index: 147955 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4443. Min Range: -2.4443
Max Act: 2.2970. Min Act: -0.1700
Data Index: 8490151 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4443. Min Range: -2.4443
Max Act: 2.2970. Min Act: -0.1700
Data Index: 4854168 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4443. Min Range: -2.4443
Max Act: 2.2806. Min Act: -0.1700
Data Index: 1174054 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4443. Min Range: -2.4443
Max Act: 2.2806. Min Act: -0.1700
Data Index: 2179430 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4443. Min Range: -2.4443
Max Act: 2.2806. Min Act: -0.1700
Data Index: 6668769 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4443. Min Range: -2.4443
Max Act: 2.2641. Min Act: -0.1700
Data Index: 7590589 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4443. Min Range: -2.4443
Max Act: 2.2476. Min Act: -0.1700
Data Index: 5380171 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4443. Min Range: -2.4443
Max Act: 2.2476. Min Act: -0.1700
Data Index: 3927177 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4443. Min Range: -2.4443
Max Act: 2.2476. Min Act: -0.1700
Data Index: 7986756 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4443. Min Range: -2.4443
Max Act: 2.2145. Min Act: -0.1700
Data Index: 6602014 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4443. Min Range: -2.4443
Max Act: 2.2310. Min Act: -0.1700
Data Index: 4408663 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #19